[ { "key": "YAQBAZ3G", "version": 549, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/YAQBAZ3G", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/YAQBAZ3G", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Saeed et al.", "parsedDate": "2024-08", "numChildren": 0 }, "data": { "key": "YAQBAZ3G", "version": 549, "itemType": "conferencePaper", "title": "From Nile Sands to Digital Hands: Machine Translation of Coptic Texts", "creators": [ { "creatorType": "author", "firstName": "Muhammed", "lastName": "Saeed" }, { "creatorType": "author", "firstName": "Asim", "lastName": "Mohamed" }, { "creatorType": "author", "firstName": "Mukhtar", "lastName": "Mohamed" }, { "creatorType": "author", "firstName": "Shady", "lastName": "Shehata" }, { "creatorType": "author", "firstName": "Muhammad", "lastName": "Abdul-Mageed" }, { "creatorType": "editor", "firstName": "Nizar", "lastName": "Habash" }, { "creatorType": "editor", "firstName": "Houda", "lastName": "Bouamor" }, { "creatorType": "editor", "firstName": "Ramy", "lastName": "Eskander" }, { "creatorType": "editor", "firstName": "Nadi", "lastName": "Tomeh" }, { "creatorType": "editor", "firstName": "Ibrahim", "lastName": "Abu Farha" }, { "creatorType": "editor", "firstName": "Ahmed", "lastName": "Abdelali" }, { "creatorType": "editor", "firstName": "Samia", "lastName": "Touileb" }, { "creatorType": "editor", "firstName": "Injy", "lastName": "Hamed" }, { "creatorType": "editor", "firstName": "Yaser", "lastName": "Onaizan" }, { "creatorType": "editor", "firstName": "Bashar", "lastName": "Alhafni" }, { "creatorType": "editor", "firstName": "Wissam", "lastName": "Antoun" }, { "creatorType": "editor", "firstName": "Salam", "lastName": "Khalifa" }, { "creatorType": "editor", "firstName": "Hatem", "lastName": "Haddad" }, { "creatorType": "editor", "firstName": "Imed", "lastName": "Zitouni" }, { "creatorType": "editor", "firstName": "Badr", "lastName": "AlKhamissi" }, { "creatorType": "editor", "firstName": "Rawan", "lastName": "Almatham" }, { "creatorType": "editor", "firstName": "Khalil", "lastName": "Mrini" } ], "abstractNote": "The Coptic language, rooted in the historical landscapes of Egypt, continues to serve as a vital liturgical medium for the Coptic Orthodox and Catholic Churches across Egypt, North Sudan, Libya, and the United States, with approximately ten million speakers worldwide. However, the scarcity of digital resources in Coptic has resulted in its exclusion from digital systems, thereby limiting its accessibility and preservation in modern technological contexts. Our research addresses this issue by developing the most extensive parallel Coptic-centered corpus to date. This corpus comprises over 8,000 parallel sentences between Arabic and Coptic, and more than 24,000 parallel sentences between English and Coptic. We have also developed the first neural machine translation system between Coptic, English, and Arabic. Lastly, we evaluate the capability of leading proprietary Large Language Models (LLMs) to translate to and from Coptic using a few-shot learning approach (in-context learning). Our code and data are available at https://github.com/UBC-NLP/copticmt.", "proceedingsTitle": "Proceedings of the Second Arabic Natural Language Processing Conference", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Bangkok, Thailand", "date": "2024-08", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "298–308", "series": "", "seriesNumber": "", "DOI": "10.18653/v1/2024.arabicnlp-1.25", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/2024.arabicnlp-1.25/", "accessDate": "2025-11-16T23:14:44Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "From Nile Sands to Digital Hands", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-11-16T23:14:44Z", "dateModified": "2025-11-16T23:14:44Z" } }, { "key": "X9VI46ZI", "version": 548, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/X9VI46ZI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/X9VI46ZI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Chaoui and Khoury", "parsedDate": "2025-08-14", "numChildren": 0 }, "data": { "key": "X9VI46ZI", "version": 548, "itemType": "preprint", "title": "Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages", "creators": [ { "creatorType": "author", "firstName": "Nasma", "lastName": "Chaoui" }, { "creatorType": "author", "firstName": "Richard", "lastName": "Khoury" } ], "abstractNote": "This paper presents the first systematic study of strategies for translating Coptic into French. Our comprehensive pipeline systematically evaluates: pivot versus direct translation, the impact of pre-training, the benefits of multi-version fine-tuning, and model robustness to noise. Utilizing aligned biblical corpora, we demonstrate that fine-tuning with a stylistically-varied and noise-aware training corpus significantly enhances translation quality. Our findings provide crucial practical insights for developing translation tools for historical languages in general.", "genre": "", "repository": "arXiv", "archiveID": "arXiv:2508.10683", "place": "", "date": "2025-08-14", "series": "", "seriesNumber": "", "DOI": "10.48550/arXiv.2508.10683", "citationKey": "", "url": "http://arxiv.org/abs/2508.10683", "accessDate": "2025-11-16T23:12:50Z", "archive": "", "archiveLocation": "", "shortTitle": "Neural Machine Translation for Coptic-French", "language": "", "libraryCatalog": "arXiv.org", "callNumber": "", "rights": "", "extra": "arXiv:2508.10683 [cs]", "tags": [ { "tag": "Computer Science - Computation and Language", "type": 1 } ], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-11-16T23:12:50Z", "dateModified": "2025-11-16T23:12:50Z" } }, { "key": "RRMCH59S", "version": 547, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/RRMCH59S", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/RRMCH59S", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Zeldes et al.", "parsedDate": "2025-08", "numChildren": 0 }, "data": { "key": "RRMCH59S", "version": 547, "itemType": "conferencePaper", "title": "A UD Treebank for Bohairic Coptic", "creators": [ { "creatorType": "author", "firstName": "Amir", "lastName": "Zeldes" }, { "creatorType": "author", "firstName": "Nina", "lastName": "Speransky" }, { "creatorType": "author", "firstName": "Nicholas E.", "lastName": "Wagner" }, { "creatorType": "author", "firstName": "Caroline T.", "lastName": "Schroeder" }, { "creatorType": "editor", "firstName": "Gosse", "lastName": "Bouma" }, { "creatorType": "editor", "firstName": "Çağrı", "lastName": "Çöltekin" } ], "abstractNote": "Despite recent advances in digital resources for other Coptic dialects, especially Sahidic, Bohairic Coptic, the main Coptic dialect for pre-Mamluk, late Byzantine Egypt, and the contemporary language of the Coptic Church, remains critically under-resourced. This paper presents and evaluates the first syntactically annotated corpus of Bohairic Coptic, sampling data from a range of works, including Biblical text, saints' lives and Christian ascetic writing. We also explore some of the main differences we observe compared to the existing UD treebank of Sahidic Coptic, the classical dialect of the language, and conduct joint and cross-dialect parsing experiments, revealing the unique nature of Bohairic as a related, but distinct variety from the more often studied Sahidic.", "proceedingsTitle": "Proceedings of the Eighth Workshop on Universal Dependencies (UDW, SyntaxFest 2025)", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Ljubljana, Slovenia", "date": "2025-08", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "59–69", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "979-8-89176-292-3", "citationKey": "", "url": "https://aclanthology.org/2025.udw-1.7/", "accessDate": "2025-11-16T23:09:59Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-11-16T23:09:59Z", "dateModified": "2025-11-16T23:09:59Z" } }, { "key": "I2IH33JV", "version": 546, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/I2IH33JV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/I2IH33JV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Miyagawa", "parsedDate": "2025-05", "numChildren": 0 }, "data": { "key": "I2IH33JV", "version": 546, "itemType": "conferencePaper", "title": "RAG-Enhanced Neural Machine Translation of Ancient Egyptian Text: A Case Study of THOTH AI", "creators": [ { "creatorType": "author", "firstName": "So", "lastName": "Miyagawa" }, { "creatorType": "editor", "firstName": "Mika", "lastName": "Hämäläinen" }, { "creatorType": "editor", "firstName": "Emily", "lastName": "Öhman" }, { "creatorType": "editor", "firstName": "Yuri", "lastName": "Bizzoni" }, { "creatorType": "editor", "firstName": "So", "lastName": "Miyagawa" }, { "creatorType": "editor", "firstName": "Khalid", "lastName": "Alnajjar" } ], "abstractNote": "This paper demonstrates how Retrieval-Augmented Generation (RAG) significantly improves translation accuracy for Middle Egyptian, a historically rich but low-resource language. We integrate a vectorized Coptic-Egyptian lexicon and morphological database into a specialized tool called THOTH AI. By supplying domain-specific linguistic knowledge to Large Language Models (LLMs) like Claude 3.5 Sonnet, our system yields translations that are more contextually grounded and semantically precise. We compare THOTH AI against various mainstream models, including Gemini 2.0, DeepSeek R1, and GPT variants, evaluating performance with BLEU, SacreBLEU, METEOR, ROUGE, and chrF. Experimental results on the coronation decree of Thutmose I (18th Dynasty) show that THOTH AI's RAG approach provides the most accurate translations, highlighting the critical value of domain knowledge in natural language processing for ancient, specialized corpora. Furthermore, we discuss how our method benefits e-learning, digital humanities, and language revitalization efforts, bridging the gap between purely data-driven approaches and expert-driven resources in historical linguistics.", "proceedingsTitle": "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Albuquerque, USA", "date": "2025-05", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "33–40", "series": "", "seriesNumber": "", "DOI": "10.18653/v1/2025.nlp4dh-1.4", "ISBN": "979-8-89176-234-3", "citationKey": "", "url": "https://aclanthology.org/2025.nlp4dh-1.4/", "accessDate": "2025-11-16T23:08:53Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "RAG-Enhanced Neural Machine Translation of Ancient Egyptian Text", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-11-16T23:08:53Z", "dateModified": "2025-11-16T23:08:53Z" } }, { "key": "JDTW7BZR", "version": 552, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/JDTW7BZR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/JDTW7BZR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Hutchings and Clivaz", "parsedDate": "2021-09-20", "numChildren": 0 }, "data": { "key": "JDTW7BZR", "version": 552, "itemType": "book", "title": "Digital Humanities and Christianity: An Introduction", "creators": [ { "creatorType": "editor", "firstName": "Tim", "lastName": "Hutchings" }, { "creatorType": "editor", "firstName": "Claire", "lastName": "Clivaz" } ], "abstractNote": "This volume provides the first comprehensive introduction to the intersections between Christianity and the digital humanities. DH is a well-established, fast-growing, multidisciplinary field producing computational applications and analytical models to enable new kinds of research. Scholars of Christianity were among the first pioneers to explore these possibilities, using digital approaches to transform the study of Christian texts, history and ideas, and innovative work is taking place today all over the world. This volume aims to celebrate and continue that legacy by bringing together 15 of the most exciting contemporary projects, grouped into four categories. “Canon, corpus and manuscript” examines physical texts and collections. “Words and meanings” explores digital approaches to language and linguistics. “Digital history” uses digital techniques to explore the Christian past, and “Theology and pedagogy” engages with digital approaches to teaching, formation and Christian ideas. This volume introduces key debates, shares exciting initiatives, and aims to encourage new innovations in analysis and communication. Christianity and the Digital Humanities is ideally suited as a starting point for students and researchers interested in this vast and complex field.", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2021-09-20", "publisher": "De Gruyter", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-3-11-057404-3", "DOI": "10.1515/9783110574043", "citationKey": "", "url": "https://www.degruyterbrill.com/document/doi/10.1515/9783110574043/html?lang=en&srsltid=AfmBOoofEMGQLSjKSMSekPwzCuMd6o2-HQXen6orRzx_z-G4N0NPqYWK", "accessDate": "2025-11-16T23:05:57Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Digital Humanities and Christianity", "language": "en", "libraryCatalog": "www.degruyterbrill.com", "callNumber": "", "rights": "De Gruyter expressly reserves the right to use all content for commercial text and data mining within the meaning of Section 44b of the German Copyright Act.", "extra": "", "tags": [ { "tag": "Bible", "type": 1 }, { "tag": "Christianity", "type": 1 }, { "tag": "Digital humanities", "type": 1 }, { "tag": "Pedagogy", "type": 1 } ], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-11-16T23:05:57Z", "dateModified": "2025-11-16T23:07:39Z" } }, { "key": "CH9SU8U6", "version": 540, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/CH9SU8U6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/CH9SU8U6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Sahala and Lincke", "parsedDate": "2024", "numChildren": 0 }, "data": { "key": "CH9SU8U6", "version": 540, "itemType": "conferencePaper", "title": "Neural Lemmatization and POS-tagging models for Coptic, Demotic and Earlier Egyptian", "creators": [ { "creatorType": "author", "firstName": "Aleksi", "lastName": "Sahala" }, { "creatorType": "author", "firstName": "Eliese-Sophia", "lastName": "Lincke" } ], "abstractNote": "We present BabyLemmatizer models for lemmatizing and POS-tagging Earlier Egyptian, Coptic and Demotic to test the performance of our pipeline for the ancient languages of Egypt.1 Of these languages, Demotic and Earlier Egyptian are known to be difficult to annotate due to their high extent of ambiguity. We report lemmatization accuracy of 86%, 91% and 99%, and XPOS-tagging accuracy of 89%, 95% and 98% for Earlier Egyptian, Demotic and Coptic, respectively.", "proceedingsTitle": "Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)", "conferenceName": "Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)", "publisher": "Association for Computational Linguistics", "place": "Hybrid in Bangkok, Thailand and online", "date": "2024", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "87-97", "series": "", "seriesNumber": "", "DOI": "10.18653/v1/2024.ml4al-1.10", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/2024.ml4al-1.10", "accessDate": "2025-03-30T19:09:54Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "DOI.org (Crossref)", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-11-16T22:58:21Z", "dateModified": "2025-11-16T22:58:21Z" } }, { "key": "VT8CH55I", "version": 540, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/VT8CH55I", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/VT8CH55I", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Sahala and Lincke", "parsedDate": "2025-05", "numChildren": 0 }, "data": { "key": "VT8CH55I", "version": 540, "itemType": "conferencePaper", "title": "Neural Models for Lemmatization and POS-Tagging of Earlier and Late Egyptian (Supporting Hieroglyphic Input) and Demotic", "creators": [ { "creatorType": "author", "firstName": "Aleksi", "lastName": "Sahala" }, { "creatorType": "author", "firstName": "Eliese-Sophia", "lastName": "Lincke" }, { "creatorType": "editor", "firstName": "Adam", "lastName": "Anderson" }, { "creatorType": "editor", "firstName": "Shai", "lastName": "Gordin" }, { "creatorType": "editor", "firstName": "Bin", "lastName": "Li" }, { "creatorType": "editor", "firstName": "Yudong", "lastName": "Liu" }, { "creatorType": "editor", "firstName": "Marco C.", "lastName": "Passarotti" }, { "creatorType": "editor", "firstName": "Rachele", "lastName": "Sprugnoli" } ], "abstractNote": "We present updated models for BabyLemma-tizer for lemmatizing and POS-tagging De-motic, Late Egyptian and Earlier Egyptian with a support for using hieroglyphs as an input. In this paper, we also use data that has not been cleaned from breakages. We achieve consistent UPOS tagging accuracy of 94% or higher and an XPOS tagging accuracy of 93% and higher for all languages. For lemmatization, which is challenging in all of our test languages due to extensive ambiguity, we demonstrate accu-racies from 77% up to 92% depending on the language and the input script.", "proceedingsTitle": "Proceedings of the Second Workshop on Ancient Language Processing", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "The Albuquerque Convention Center, Laguna", "date": "2025-05", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "99–104", "series": "", "seriesNumber": "", "DOI": "10.18653/v1/2025.alp-1.12", "ISBN": "979-8-89176-235-0", "citationKey": "", "url": "https://aclanthology.org/2025.alp-1.12/", "accessDate": "2025-11-16T22:57:04Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2025-11-16T22:57:08Z", "dateModified": "2025-11-16T22:57:08Z" } }, { "key": "LMLZQC7G", "version": 534, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/LMLZQC7G", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/LMLZQC7G", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Liu et al.", "parsedDate": "2025-04-11", "numChildren": 0 }, "data": { "key": "LMLZQC7G", "version": 534, "itemType": "journalArticle", "title": "Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing", "creators": [ { "creatorType": "author", "firstName": "Jianjian", "lastName": "Liu" }, { "creatorType": "author", "firstName": "Zhengtao", "lastName": "Yu" }, { "creatorType": "author", "firstName": "Ying", "lastName": "Li" }, { "creatorType": "author", "firstName": "Yuxin", "lastName": "Huang" }, { "creatorType": "author", "firstName": "Shengxiang", "lastName": "Gao" } ], "abstractNote": "Pre-trained language models enhanced parsers have achieved outstanding performance in rich-resource languages. Cross-lingual dependency parsing aims to learn useful knowledge from high-resource languages to alleviate data scarcity in low-resource languages. However, effectively reducing the syntactic structure distributional bias and excavating the commonalities among languages is the key challenge for cross-lingual dependency parsing. To address this issue, we propose novel dynamic syntactic feature filtering and injecting networks based on the typical shared-private model that employs one shared and two private encoders to separate source and target language features. Concretely, a Language-Specific Filtering Network (LSFN) on private encoders emphasizes helpful information and ignores the irrelevant or harmful parts of it from the source language. Meanwhile, a Language-Invariant Injecting Network (LIIN) on the shared encoder integrates the advantages of BiLSTM and improved Transformer encoders to transcend language boundaries, thus amplifying syntactic commonalities across languages. Experiments on seven benchmark datasets show that our model achieves an average absolute gain of 1.84 UAS and 3.43 LAS compared with the shared-private model. Comparative experiments validate that both LSFN and LIIN components are complementary in transferring beneficial knowledge from source to target languages. Detailed analyses highlight that our model can effectively capture linguistic commonalities and mitigate the effect of distributional bias, showcasing its robustness and efficacy.", "publicationTitle": "Proceedings of the AAAI Conference on Artificial Intelligence", "publisher": "", "place": "", "date": "2025-04-11", "volume": "39", "issue": "23", "section": "", "partNumber": "", "partTitle": "", "pages": "24614-24622", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1609/aaai.v39i23.34641", "citationKey": "", "url": "https://ojs.aaai.org/index.php/AAAI/article/view/34641", "accessDate": "2025-04-20T18:57:05Z", "PMID": "", "PMCID": "", "ISSN": "2374-3468", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "ojs.aaai.org", "callNumber": "", "rights": "Copyright (c) 2025 Association for the Advancement of Artificial Intelligence", "extra": "Number: 23", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-04-20T18:57:15Z", "dateModified": "2025-04-20T18:57:15Z" } }, { "key": "Z4ZARUS2", "version": 533, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/Z4ZARUS2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/Z4ZARUS2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Horner", "parsedDate": "1898", "numChildren": 0 }, "data": { "key": "Z4ZARUS2", "version": 533, "itemType": "book", "title": "The Coptic version of the New Testament in the northern dialect otherwise called Memphitic and Bohairic : with introduction, critical apparatus, and literal English translation", "creators": [ { "creatorType": "author", "firstName": "George William", "lastName": "Horner" }, { "creatorType": "contributor", "name": "Robarts - University of Toronto" } ], "abstractNote": "Vol. 1. The Gospels of S. Matthew and S. Mark; edited from MS. Huntington 17 in the Bodleian Library.- Vol. 2. The Gospels of S. Luke and S. John edited from MS. Huntington 17 in the Bodleian Library. The Epistles of S. Paul; edited from MS. Oriental 424 in the British Museum.- Vol. 4. The Catholic Epistles and the Acts of the Apostles; edited from MS. Oriental 424; the Apocalypse; edited from MS Curzon 128 in the care of the British Museum; 26", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "1898-1905", "publisher": "Oxford : Clarendon Press", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "644", "ISBN": "", "DOI": "", "citationKey": "", "url": "http://archive.org/details/copticversionofn01hornuoft", "accessDate": "2025-04-01T01:08:56Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "The Coptic version of the New Testament in the northern dialect otherwise called Memphitic and Bohairic", "language": "cop", "libraryCatalog": "Internet Archive", "callNumber": "AEK-6882", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2025-04-01T01:08:56Z", "dateModified": "2025-04-01T01:08:56Z" } }, { "key": "4U689RKA", "version": 533, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/4U689RKA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/4U689RKA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Horner", "parsedDate": "1898", "numChildren": 0 }, "data": { "key": "4U689RKA", "version": 533, "itemType": "book", "title": "The Coptic version of the New Testament in the northern dialect", "creators": [ { "creatorType": "author", "firstName": "George William", "lastName": "Horner" }, { "creatorType": "contributor", "name": "Princeton Theological Seminary Library" } ], "abstractNote": "1. Gospels Matthew and Mark, ed. from Ms. Huntington 17 in the Bodleian library.- 2. Gospels of Luke and John, ed. from Ms. Huntington 17 in the Bodleian library.- 3. Epistles of S. Paul ed. from Ms. Oriental 424 in the British museum.- 4. Catholic epistles and the Acts of the Apostles, ed. from Ms. Oriental 424, the Apocalypse, ed. from Ms. Curzon 128 in the care of the British museum", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "1898", "publisher": "London, Claredon press", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "716", "ISBN": "", "DOI": "", "citationKey": "", "url": "http://archive.org/details/copticversionofn03horn", "accessDate": "2025-04-01T01:08:02Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "Coptic.", "libraryCatalog": "Internet Archive", "callNumber": "148094", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2025-04-01T01:08:02Z", "dateModified": "2025-04-01T01:08:02Z" } }, { "key": "G5AW6QXK", "version": 530, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/G5AW6QXK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/G5AW6QXK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Smith and Hulden", "parsedDate": "2016-05", "numChildren": 0 }, "data": { "key": "G5AW6QXK", "version": 530, "itemType": "conferencePaper", "title": "Morphological Analysis of Sahidic Coptic for Automatic Glossing", "creators": [ { "creatorType": "author", "firstName": "Daniel", "lastName": "Smith" }, { "creatorType": "author", "firstName": "Mans", "lastName": "Hulden" }, { "creatorType": "editor", "firstName": "Nicoletta", "lastName": "Calzolari" }, { "creatorType": "editor", "firstName": "Khalid", "lastName": "Choukri" }, { "creatorType": "editor", "firstName": "Thierry", "lastName": "Declerck" }, { "creatorType": "editor", "firstName": "Sara", "lastName": "Goggi" }, { "creatorType": "editor", "firstName": "Marko", "lastName": "Grobelnik" }, { "creatorType": "editor", "firstName": "Bente", "lastName": "Maegaard" }, { "creatorType": "editor", "firstName": "Joseph", "lastName": "Mariani" }, { "creatorType": "editor", "firstName": "Helene", "lastName": "Mazo" }, { "creatorType": "editor", "firstName": "Asuncion", "lastName": "Moreno" }, { "creatorType": "editor", "firstName": "Jan", "lastName": "Odijk" }, { "creatorType": "editor", "firstName": "Stelios", "lastName": "Piperidis" } ], "abstractNote": "We report on the implementation of a morphological analyzer for the Sahidic dialect of Coptic, a now extinct Afro-Asiatic language. The system is developed in the finite-state paradigm. The main purpose of the project is provide a method by which scholars and linguists can semi-automatically gloss extant texts written in Sahidic. Since a complete lexicon containing all attested forms in different manuscripts requires significant expertise in Coptic spanning almost 1,000 years, we have equipped the analyzer with a core lexicon and extended it with a “guesser” ability to capture out-of-vocabulary items in any inflection. We also suggest an ASCII transliteration for the language. A brief evaluation is provided.", "proceedingsTitle": "Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC`16)", "conferenceName": "LREC 2016", "publisher": "European Language Resources Association (ELRA)", "place": "Portorož, Slovenia", "date": "2016-05", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "2584–2588", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/L16-1411/", "accessDate": "2025-03-30T19:21:31Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:21:31Z", "dateModified": "2025-03-30T19:21:31Z" } }, { "key": "BF69H4CF", "version": 529, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/BF69H4CF", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/BF69H4CF", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Ponti et al.", "parsedDate": "2018-07", "numChildren": 0 }, "data": { "key": "BF69H4CF", "version": 529, "itemType": "conferencePaper", "title": "Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP", "creators": [ { "creatorType": "author", "firstName": "Edoardo Maria", "lastName": "Ponti" }, { "creatorType": "author", "firstName": "Roi", "lastName": "Reichart" }, { "creatorType": "author", "firstName": "Anna", "lastName": "Korhonen" }, { "creatorType": "author", "firstName": "Ivan", "lastName": "Vulić" }, { "creatorType": "editor", "firstName": "Iryna", "lastName": "Gurevych" }, { "creatorType": "editor", "firstName": "Yusuke", "lastName": "Miyao" } ], "abstractNote": "The transfer or share of knowledge between languages is a potential solution to resource scarcity in NLP. However, the effectiveness of cross-lingual transfer can be challenged by variation in syntactic structures. Frameworks such as Universal Dependencies (UD) are designed to be cross-lingually consistent, but even in carefully designed resources trees representing equivalent sentences may not always overlap. In this paper, we measure cross-lingual syntactic variation, or anisomorphism, in the UD treebank collection, considering both morphological and structural properties. We show that reducing the level of anisomorphism yields consistent gains in cross-lingual transfer tasks. We introduce a source language selection procedure that facilitates effective cross-lingual parser transfer, and propose a typologically driven method for syntactic tree processing which reduces anisomorphism. Our results show the effectiveness of this method for both machine translation and cross-lingual sentence similarity, demonstrating the importance of syntactic structure compatibility for boosting cross-lingual transfer in NLP.", "proceedingsTitle": "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", "conferenceName": "ACL 2018", "publisher": "Association for Computational Linguistics", "place": "Melbourne, Australia", "date": "2018-07", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1531–1542", "series": "", "seriesNumber": "", "DOI": "10.18653/v1/P18-1142", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/P18-1142/", "accessDate": "2025-03-30T19:20:55Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:20:55Z", "dateModified": "2025-03-30T19:20:55Z" } }, { "key": "EFQGYY34", "version": 528, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/EFQGYY34", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/EFQGYY34", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Ebrahimi and Kann", "parsedDate": "2021-08", "numChildren": 0 }, "data": { "key": "EFQGYY34", "version": 528, "itemType": "conferencePaper", "title": "How to Adapt Your Pretrained Multilingual Model to 1600 Languages", "creators": [ { "creatorType": "author", "firstName": "Abteen", "lastName": "Ebrahimi" }, { "creatorType": "author", "firstName": "Katharina", "lastName": "Kann" }, { "creatorType": "editor", "firstName": "Chengqing", "lastName": "Zong" }, { "creatorType": "editor", "firstName": "Fei", "lastName": "Xia" }, { "creatorType": "editor", "firstName": "Wenjie", "lastName": "Li" }, { "creatorType": "editor", "firstName": "Roberto", "lastName": "Navigli" } ], "abstractNote": "Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining. While methods exist to improve performance for unseen languages, they have almost exclusively been evaluated using amounts of raw text only available for a small fraction of the world`s languages. In this paper, we evaluate the performance of existing methods to adapt PMMs to new languages using a resource available for close to 1600 languages: the New Testament. This is challenging for two reasons: (1) the small corpus size, and (2) the narrow domain. While performance drops for all approaches, we surprisingly still see gains of up to 17.69% accuracy for part-of-speech tagging and 6.29 F1 for NER on average over all languages as compared to XLM-R. Another unexpected finding is that continued pretraining, the simplest approach, performs best. Finally, we perform a case study to disentangle the effects of domain and size and to shed light on the influence of the finetuning source language.", "proceedingsTitle": "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)", "conferenceName": "ACL-IJCNLP 2021", "publisher": "Association for Computational Linguistics", "place": "Online", "date": "2021-08", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "4555–4567", "series": "", "seriesNumber": "", "DOI": "10.18653/v1/2021.acl-long.351", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/2021.acl-long.351/", "accessDate": "2025-03-30T19:20:22Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:20:22Z", "dateModified": "2025-03-30T19:20:22Z" } }, { "key": "R45EZQQ8", "version": 527, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/R45EZQQ8", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/R45EZQQ8", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Antonio Díaz Hernández and Carlo Passarotti", "parsedDate": "2024-12", "numChildren": 0 }, "data": { "key": "R45EZQQ8", "version": 527, "itemType": "conferencePaper", "title": "Developing the Egyptian-UJaen Treebank", "creators": [ { "creatorType": "author", "firstName": "Roberto", "lastName": "Antonio Díaz Hernández" }, { "creatorType": "author", "firstName": "Marco", "lastName": "Carlo Passarotti" }, { "creatorType": "editor", "firstName": "Daniel", "lastName": "Dakota" }, { "creatorType": "editor", "firstName": "Sarah", "lastName": "Jablotschkin" }, { "creatorType": "editor", "firstName": "Sandra", "lastName": "Kübler" }, { "creatorType": "editor", "firstName": "Heike", "lastName": "Zinsmeister" } ], "abstractNote": "This paper presents preliminary results of the development of the Egyptian-UJaen treebank, the first dependency treebank created for pre-Coptic Egyptian in Universal Dependencies. It describes the current state of the treebank, explains the approach adopted for the morphosyntactic annotation and discusses some issues concerning the adoption of the CoNLL-U format for the annotation of Egyptian texts. This treebank will surely become a useful linguistic tool for understanding the synchronic and dia- chronic use of pre-Coptic Egyptian.", "proceedingsTitle": "Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024)", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Hamburg,Germany", "date": "2024-12", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1–10", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/2024.tlt-1.1/", "accessDate": "2025-03-30T19:19:19Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:19:19Z", "dateModified": "2025-03-30T19:19:19Z" } }, { "key": "78EAWEIW", "version": 526, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/78EAWEIW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/78EAWEIW", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/86149/items/UCYNAHUB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "78EAWEIW", "version": 526, "parentItem": "UCYNAHUB", "itemType": "note", "note": "Comment: LREC-COLING 2024", "tags": [], "relations": {}, "dateAdded": "2025-03-30T19:18:31Z", "dateModified": "2025-03-30T19:18:31Z" } }, { "key": "UCYNAHUB", "version": 526, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/UCYNAHUB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/UCYNAHUB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Weissweiler et al.", "parsedDate": "2024-03-26", "numChildren": 1 }, "data": { "key": "UCYNAHUB", "version": 526, "itemType": "preprint", "title": "UCxn: Typologically Informed Annotation of Constructions Atop Universal Dependencies", "creators": [ { "creatorType": "author", "firstName": "Leonie", "lastName": "Weissweiler" }, { "creatorType": "author", "firstName": "Nina", "lastName": "Böbel" }, { "creatorType": "author", "firstName": "Kirian", "lastName": "Guiller" }, { "creatorType": "author", "firstName": "Santiago", "lastName": "Herrera" }, { "creatorType": "author", "firstName": "Wesley", "lastName": "Scivetti" }, { "creatorType": "author", "firstName": "Arthur", "lastName": "Lorenzi" }, { "creatorType": "author", "firstName": "Nurit", "lastName": "Melnik" }, { "creatorType": "author", "firstName": "Archna", "lastName": "Bhatia" }, { "creatorType": "author", "firstName": "Hinrich", "lastName": "Schütze" }, { "creatorType": "author", "firstName": "Lori", "lastName": "Levin" }, { "creatorType": "author", "firstName": "Amir", "lastName": "Zeldes" }, { "creatorType": "author", "firstName": "Joakim", "lastName": "Nivre" }, { "creatorType": "author", "firstName": "William", "lastName": "Croft" }, { "creatorType": "author", "firstName": "Nathan", "lastName": "Schneider" } ], "abstractNote": "The Universal Dependencies (UD) project has created an invaluable collection of treebanks with contributions in over 140 languages. However, the UD annotations do not tell the full story. Grammatical constructions that convey meaning through a particular combination of several morphosyntactic elements -- for example, interrogative sentences with special markers and/or word orders -- are not labeled holistically. We argue for (i) augmenting UD annotations with a 'UCxn' annotation layer for such meaning-bearing grammatical constructions, and (ii) approaching this in a typologically informed way so that morphosyntactic strategies can be compared across languages. As a case study, we consider five construction families in ten languages, identifying instances of each construction in UD treebanks through the use of morphosyntactic patterns. In addition to findings regarding these particular constructions, our study yields important insights on methodology for describing and identifying constructions in language-general and language-particular ways, and lays the foundation for future constructional enrichment of UD treebanks.", "genre": "", "repository": "arXiv", "archiveID": "arXiv:2403.17748", "place": "", "date": "2024-03-26", "series": "", "seriesNumber": "", "DOI": "10.48550/arXiv.2403.17748", "citationKey": "", "url": "http://arxiv.org/abs/2403.17748", "accessDate": "2025-03-30T19:18:31Z", "archive": "", "archiveLocation": "", "shortTitle": "UCxn", "language": "", "libraryCatalog": "arXiv.org", "callNumber": "", "rights": "", "extra": "arXiv:2403.17748 [cs]", "tags": [ { "tag": "Computer Science - Computation and Language", "type": 1 } ], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:18:31Z", "dateModified": "2025-03-30T19:18:31Z" } }, { "key": "ZHA8H8DU", "version": 525, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/ZHA8H8DU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/ZHA8H8DU", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/86149/items/WX8TZ7NX", "type": "application/json" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "ZHA8H8DU", "version": 525, "parentItem": "WX8TZ7NX", "itemType": "note", "note": "Comment: Extended version of the paper that is published in Proceedings of the Fifth Workshop on Universal Dependencies (UDW, SyntaxFest 2021), with additional sections on adverbial NPs and numbers/measurements", "tags": [], "relations": {}, "dateAdded": "2025-03-30T19:17:43Z", "dateModified": "2025-03-30T19:17:43Z" } }, { "key": "WX8TZ7NX", "version": 525, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/WX8TZ7NX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/WX8TZ7NX", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Schneider and Zeldes", "parsedDate": "2021-12-25", "numChildren": 1 }, "data": { "key": "WX8TZ7NX", "version": 525, "itemType": "preprint", "title": "Mischievous Nominal Constructions in Universal Dependencies", "creators": [ { "creatorType": "author", "firstName": "Nathan", "lastName": "Schneider" }, { "creatorType": "author", "firstName": "Amir", "lastName": "Zeldes" } ], "abstractNote": "While the highly multilingual Universal Dependencies (UD) project provides extensive guidelines for clausal structure as well as structure within canonical nominal phrases, a standard treatment is lacking for many \"mischievous\" nominal phenomena that break the mold. As a result, numerous inconsistencies within and across corpora can be found, even in languages with extensive UD treebanking work, such as English. This paper surveys the kinds of mischievous nominal expressions attested in English UD corpora and proposes solutions primarily with English in mind, but which may offer paths to solutions for a variety of UD languages.", "genre": "", "repository": "arXiv", "archiveID": "arXiv:2108.12928", "place": "", "date": "2021-12-25", "series": "", "seriesNumber": "", "DOI": "10.48550/arXiv.2108.12928", "citationKey": "", "url": "http://arxiv.org/abs/2108.12928", "accessDate": "2025-03-30T19:17:43Z", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "arXiv.org", "callNumber": "", "rights": "", "extra": "arXiv:2108.12928 [cs]", "tags": [ { "tag": "Computer Science - Computation and Language", "type": 1 } ], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:17:43Z", "dateModified": "2025-03-30T19:17:43Z" } }, { "key": "EZMT9H38", "version": 524, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/EZMT9H38", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/EZMT9H38", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Swanson and Tyers", "parsedDate": "2022-06", "numChildren": 0 }, "data": { "key": "EZMT9H38", "version": 524, "itemType": "conferencePaper", "title": "A Universal Dependencies Treebank of Ancient Hebrew", "creators": [ { "creatorType": "author", "firstName": "Daniel", "lastName": "Swanson" }, { "creatorType": "author", "firstName": "Francis", "lastName": "Tyers" }, { "creatorType": "editor", "firstName": "Nicoletta", "lastName": "Calzolari" }, { "creatorType": "editor", "firstName": "Frédéric", "lastName": "Béchet" }, { "creatorType": "editor", "firstName": "Philippe", "lastName": "Blache" }, { "creatorType": "editor", "firstName": "Khalid", "lastName": "Choukri" }, { "creatorType": "editor", "firstName": "Christopher", "lastName": "Cieri" }, { "creatorType": "editor", "firstName": "Thierry", "lastName": "Declerck" }, { "creatorType": "editor", "firstName": "Sara", "lastName": "Goggi" }, { "creatorType": "editor", "firstName": "Hitoshi", "lastName": "Isahara" }, { "creatorType": "editor", "firstName": "Bente", "lastName": "Maegaard" }, { "creatorType": "editor", "firstName": "Joseph", "lastName": "Mariani" }, { "creatorType": "editor", "firstName": "Hélène", "lastName": "Mazo" }, { "creatorType": "editor", "firstName": "Jan", "lastName": "Odijk" }, { "creatorType": "editor", "firstName": "Stelios", "lastName": "Piperidis" } ], "abstractNote": "In this paper we present the initial construction of a Universal Dependencies treebank with morphological annotations of Ancient Hebrew containing portions of the Hebrew Scriptures (1579 sentences, 27K tokens) for use in comparative study with ancient translations and for analysis of the development of Hebrew syntax. We construct this treebank by applying a rule-based parser (300 rules) to an existing morphologically-annotated corpus with minimal constituency structure and manually verifying the output and present the results of this semi-automated annotation process and some of the annotation decisions made in the process of applying the UD guidelines to a new language.", "proceedingsTitle": "Proceedings of the Thirteenth Language Resources and Evaluation Conference", "conferenceName": "LREC 2022", "publisher": "European Language Resources Association", "place": "Marseille, France", "date": "2022-06", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "2353–2361", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/2022.lrec-1.252/", "accessDate": "2025-03-30T19:16:28Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:16:28Z", "dateModified": "2025-03-30T19:16:28Z" } }, { "key": "5RIYKNSL", "version": 523, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/5RIYKNSL", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/5RIYKNSL", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "5RIYKNSL", "version": 523, "itemType": "webpage", "title": "", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "https://ufal.mff.cuni.cz/biblio/attachments/2024-zeman-m3156218524711462162.pdf", "accessDate": "2025-03-30T19:14:42Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:14:42Z", "dateModified": "2025-03-30T19:14:42Z" } }, { "key": "F3BTN9QA", "version": 522, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/F3BTN9QA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/F3BTN9QA", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/86149/items/L2BQJL67", "type": "application/json" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "F3BTN9QA", "version": 522, "parentItem": "L2BQJL67", "itemType": "note", "note": "Comment: This is a peer reviewed article that has been presented in The International Conference on Agglutinative Language Technologies as a challenge of Natural Language Processing (ALTNLP) 2022", "tags": [], "relations": {}, "dateAdded": "2025-03-30T19:12:23Z", "dateModified": "2025-03-30T19:12:23Z" } }, { "key": "L2BQJL67", "version": 522, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/L2BQJL67", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/L2BQJL67", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Marşan et al.", "parsedDate": "2022-07-24", "numChildren": 1 }, "data": { "key": "L2BQJL67", "version": 522, "itemType": "preprint", "title": "Enhancements to the BOUN Treebank Reflecting the Agglutinative Nature of Turkish", "creators": [ { "creatorType": "author", "firstName": "Büşra", "lastName": "Marşan" }, { "creatorType": "author", "firstName": "Salih Furkan", "lastName": "Akkurt" }, { "creatorType": "author", "firstName": "Muhammet", "lastName": "Şen" }, { "creatorType": "author", "firstName": "Merve", "lastName": "Gürbüz" }, { "creatorType": "author", "firstName": "Onur", "lastName": "Güngör" }, { "creatorType": "author", "firstName": "Şaziye Betül", "lastName": "Özateş" }, { "creatorType": "author", "firstName": "Suzan", "lastName": "Üsküdarlı" }, { "creatorType": "author", "firstName": "Arzucan", "lastName": "Özgür" }, { "creatorType": "author", "firstName": "Tunga", "lastName": "Güngör" }, { "creatorType": "author", "firstName": "Balkız", "lastName": "Öztürk" } ], "abstractNote": "In this study, we aim to offer linguistically motivated solutions to resolve the issues of the lack of representation of null morphemes, highly productive derivational processes, and syncretic morphemes of Turkish in the BOUN Treebank without diverging from the Universal Dependencies framework. In order to tackle these issues, new annotation conventions were introduced by splitting certain lemmas and employing the MISC (miscellaneous) tab in the UD framework to denote derivation. Representational capabilities of the re-annotated treebank were tested on a LSTM-based dependency parser and an updated version of the BoAT Tool is introduced.", "genre": "", "repository": "arXiv", "archiveID": "arXiv:2207.11782", "place": "", "date": "2022-07-24", "series": "", "seriesNumber": "", "DOI": "10.48550/arXiv.2207.11782", "citationKey": "", "url": "http://arxiv.org/abs/2207.11782", "accessDate": "2025-03-30T19:12:23Z", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "arXiv.org", "callNumber": "", "rights": "", "extra": "arXiv:2207.11782 [cs]", "tags": [ { "tag": "Computer Science - Computation and Language", "type": 1 } ], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:12:23Z", "dateModified": "2025-03-30T19:12:23Z" } }, { "key": "KUH2H9AT", "version": 521, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/KUH2H9AT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/KUH2H9AT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Tran and Miyao", "parsedDate": "2022-06", "numChildren": 0 }, "data": { "key": "KUH2H9AT", "version": 521, "itemType": "conferencePaper", "title": "Development of a Multilingual CCG Treebank via Universal Dependencies Conversion", "creators": [ { "creatorType": "author", "firstName": "Tu-Anh", "lastName": "Tran" }, { "creatorType": "author", "firstName": "Yusuke", "lastName": "Miyao" }, { "creatorType": "editor", "firstName": "Nicoletta", "lastName": "Calzolari" }, { "creatorType": "editor", "firstName": "Frédéric", "lastName": "Béchet" }, { "creatorType": "editor", "firstName": "Philippe", "lastName": "Blache" }, { "creatorType": "editor", "firstName": "Khalid", "lastName": "Choukri" }, { "creatorType": "editor", "firstName": "Christopher", "lastName": "Cieri" }, { "creatorType": "editor", "firstName": "Thierry", "lastName": "Declerck" }, { "creatorType": "editor", "firstName": "Sara", "lastName": "Goggi" }, { "creatorType": "editor", "firstName": "Hitoshi", "lastName": "Isahara" }, { "creatorType": "editor", "firstName": "Bente", "lastName": "Maegaard" }, { "creatorType": "editor", "firstName": "Joseph", "lastName": "Mariani" }, { "creatorType": "editor", "firstName": "Hélène", "lastName": "Mazo" }, { "creatorType": "editor", "firstName": "Jan", "lastName": "Odijk" }, { "creatorType": "editor", "firstName": "Stelios", "lastName": "Piperidis" } ], "abstractNote": "This paper introduces an algorithm to convert Universal Dependencies (UD) treebanks to Combinatory Categorial Grammar (CCG) treebanks. As CCG encodes almost all grammatical information into the lexicon, obtaining a high-quality CCG derivation from a dependency tree is a challenging task. Our algorithm relies on hand-crafted rules to assign categories to constituents, and a non-statistical parser to derive full CCG parses given the assigned categories. To evaluate our converted treebanks, we perform lexical, sentential, and syntactic rule coverage analysis, as well as CCG parsing experiments. Finally, we discuss how our method handles complex constructions, and propose possible future extensions.", "proceedingsTitle": "Proceedings of the Thirteenth Language Resources and Evaluation Conference", "conferenceName": "LREC 2022", "publisher": "European Language Resources Association", "place": "Marseille, France", "date": "2022-06", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "5220–5233", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "https://aclanthology.org/2022.lrec-1.560/", "accessDate": "2025-03-30T19:11:45Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACLWeb", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:11:45Z", "dateModified": "2025-03-30T19:11:45Z" } }, { "key": "YGQKPI2V", "version": 520, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/YGQKPI2V", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/YGQKPI2V", "type": "text/html" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "creatorSummary": "Speransky", "parsedDate": "2023", "numChildren": 0 }, "data": { "key": "YGQKPI2V", "version": 520, "itemType": "journalArticle", "title": "Transitivity and Aspect in Sahidic Coptic: Studies in the Morphosyntax of Native and Greek-Origin Verbs", "creators": [ { "creatorType": "author", "firstName": "Nina", "lastName": "Speransky" } ], "abstractNote": "The study clarifies certain details of the Coptic verbal system, such as diathetic classes of labile verbs, semantic classes of non-labile mutable verbs, stative: infinitive opposition, the functional range of the periphrastic construction, integration of Greek loan verbs into Coptic valency alternation system and the role of the loaned morphology in that system. In all these problems, we find manifested the interaction between two grammatical categories, transitivity and aspect.\nThe introductory chapter briefly states the research objectives and gives a general overview of the linguistic material and theory employed. \nThe first chapter studies major regularities in the transitivity alternations of native Egyptian verbs. Defining the Coptic conjugation system by two parameters, aspect and transitivity, I examine the functions of the absolute infinitive as the only unmarked form opposed, on the one hand, to transitive eventive construct forms, and on the other hand, to intransitive stative. The system of conjugation patterns is analyzed as a templatic system where a specific conjugation pattern ascribes not only tense, aspect, and modus, but also voice to an unmarked verbal form. Finally, the native verbs are classified into four groups based on the formal criteria of mutability and lability, and this classification is found to correlate with the semantic one based on the agentivity and telicity of verbal lexemes. I also look into the diachrony of the aspect-transitivity cluster and use the two-parameter model to explain various synchronic anomalies of Coptic verbal valency.\nThe second chapter looks into semantic and grammatical factors triggering the use of the periphrastic pattern <ϣⲱⲡⲉ + circumstantial clause> which is shown to fulfil the whole range of functions, from punctual passive to resultative, depending on the lexical properties of the verb.\nThe third chapter explores the diathesis of Greek loan verbs in Sahidic. Valency-changing devices for Greek verbs are examined and compared with those operating on native verbs. The occasional use of Greek middle-passive suffix is analyzed as the vestige of parallel system borrowing.", "publicationTitle": "", "publisher": "", "place": "", "date": "2023", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.37011/studmon.26", "citationKey": "", "url": "https://refubium.fu-berlin.de/handle/fub188/37464", "accessDate": "2025-03-30T19:10:56Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Transitivity and Aspect in Sahidic Coptic", "language": "eng", "libraryCatalog": "refubium.fu-berlin.de", "callNumber": "", "rights": "https://creativecommons.org/licenses/by/4.0/", "extra": "Accepted: 2023-02-03T11:47:38Z\nISBN: 9783943955910", "tags": [], "collections": [ "BXV4KHSS" ], "relations": {}, "dateAdded": "2025-03-30T19:10:56Z", "dateModified": "2025-03-30T19:10:56Z" } }, { "key": "IBLMX64D", "version": 519, "library": { "type": "group", "id": 86149, "name": "Coptic Scriptorium", "links": { "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/86149/items/IBLMX64D", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/coptic_scriptorium/items/IBLMX64D", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/86149/items/27N8VX9B", "type": "application/json" } }, "meta": { "createdByUser": { "id": 264850, "username": "ctschroeder", "name": "Caroline T. Schroeder", "links": { "alternate": { "href": "https://www.zotero.org/ctschroeder", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "IBLMX64D", "version": 519, "parentItem": "27N8VX9B", "itemType": "note", "note": "Comment: 9 pages, 5 figures. Accepted to LAW-XVIII", "tags": [], "relations": {}, "dateAdded": "2025-03-30T19:10:42Z", "dateModified": "2025-03-30T19:10:42Z" } } ]