They adapt an existing POS tagger.
", "tags": [], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/QCAB563N" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "RQ9RT62I", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/RQ9RT62I", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/RQ9RT62I", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/331416/items/DVSXWPMF", "type": "application/json" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "RQ9RT62I", "version": 2, "parentItem": "DVSXWPMF", "itemType": "note", "note": "POSLDA method: keeps track of part of speech as well as actual words
", "tags": [], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/4993BANN" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "X49FTGPQ", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/X49FTGPQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/X49FTGPQ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/331416/items/IFMU5GXB", "type": "application/json" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "X49FTGPQ", "version": 2, "parentItem": "IFMU5GXB", "itemType": "note", "note": "K-Nearest-Neighbors approach
\nChallenges for tweets:
\n", "tags": [], "collections": [ "BIPVITQQ" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/QJ5DSMRU" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "3ZDET5TR", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/3ZDET5TR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/3ZDET5TR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Shibui and Sakurai", "parsedDate": "2004-12", "numChildren": 0 }, "data": { "key": "3ZDET5TR", "version": 2, "itemType": "journalArticle", "title": "FrameNet-Based Shallow Semantic Parsing with a POS Tagger (Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ and IEICE-SIGAI on Active Mining) – (Session 11: Artificial Intelligence 2)", "creators": [ { "creatorType": "author", "firstName": "Nobukazu", "lastName": "Shibui" }, { "creatorType": "author", "firstName": "Akito", "lastName": "Sakurai" } ], "abstractNote": "", "publicationTitle": "知識ベ-スシステム研究会", "publisher": "", "place": "", "date": "December 2004", "volume": "67", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "187-190", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://ci.nii.ac.jp/naid/40006531145/", "accessDate": "2015-02-23T18:29:13Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "FrameNet-Based Shallow Semantic Parsing with a POS Tagger (Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ and IEICE-SIGAI on Active Mining) – (Session 11", "language": "", "libraryCatalog": "CiNii", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "BIPVITQQ" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/HP9M2AQ9" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "N6DCN4RH", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/N6DCN4RH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/N6DCN4RH", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Ritter et al.", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "N6DCN4RH", "version": 2, "itemType": "conferencePaper", "title": "Open Domain Event Extraction from Twitter", "creators": [ { "creatorType": "author", "firstName": "Alan", "lastName": "Ritter" }, { "creatorType": "author", "name": "Mausam" }, { "creatorType": "author", "firstName": "Oren", "lastName": "Etzioni" }, { "creatorType": "author", "firstName": "Sam", "lastName": "Clark" } ], "abstractNote": "Tweets are the most up-to-date and inclusive stream of in- formation and commentary on current events, but they are also fragmented and noisy, motivating the need for systems that can extract, aggregate and categorize important events. Previous work on extracting structured representations of events has focused largely on newswire text; Twitter's unique characteristics present new challenges and opportunities for open-domain event extraction. This paper describes TwiCal-- the first open-domain event-extraction and categorization system for Twitter. We demonstrate that accurately extracting an open-domain calendar of significant events from Twitter is indeed feasible. In addition, we present a novel approach for discovering important event categories and classifying extracted events based on latent variable models. By leveraging large volumes of unlabeled data, our approach achieves a 14% increase in maximum F1 over a supervised baseline. A continuously updating demonstration of our system can be viewed at http://statuscalendar.com; Our NLP tools are available at http://github.com/aritter/ twitter_nlp.", "proceedingsTitle": "Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2012", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1104–1112", "series": "KDD '12", "seriesNumber": "", "DOI": "10.1145/2339530.2339704", "ISBN": "978-1-4503-1462-6", "citationKey": "", "url": "http://doi.acm.org/10.1145/2339530.2339704", "accessDate": "2015-02-23T18:04:54Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "information extraction", "type": 1 }, { "tag": "social media", "type": 1 } ], "collections": [ "MMIA937V" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/BCJ8SVG8" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "S3U3ERVD", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/S3U3ERVD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/S3U3ERVD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Popescu and Pennacchiotti", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "S3U3ERVD", "version": 2, "itemType": "conferencePaper", "title": "Detecting Controversial Events from Twitter", "creators": [ { "creatorType": "author", "firstName": "Ana-Maria", "lastName": "Popescu" }, { "creatorType": "author", "firstName": "Marco", "lastName": "Pennacchiotti" } ], "abstractNote": "Social media provides researchers with continuously updated information about developments of interest to large audiences. This paper addresses the task of identifying controversial events using Twitter as a starting point: we propose 3 models for this task and report encouraging initial results.", "proceedingsTitle": "Proceedings of the 19th ACM International Conference on Information and Knowledge Management", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1873–1876", "series": "CIKM '10", "seriesNumber": "", "DOI": "10.1145/1871437.1871751", "ISBN": "978-1-4503-0099-5", "citationKey": "", "url": "http://doi.acm.org/10.1145/1871437.1871751", "accessDate": "2015-02-20T23:24:43Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "controversy", "type": 1 }, { "tag": "event mining", "type": 1 }, { "tag": "opinion mining", "type": 1 } ], "collections": [ "FW9Q2H2W", "QZBMSSWC" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/B3E92ZF8" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "3D7C6BIH", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/3D7C6BIH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/3D7C6BIH", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Gadde et al.", "parsedDate": "2011", "numChildren": 1 }, "data": { "key": "3D7C6BIH", "version": 2, "itemType": "conferencePaper", "title": "Adapting a WSJ Trained Part-of-speech Tagger to Noisy Text: Preliminary Results", "creators": [ { "creatorType": "author", "firstName": "Phani", "lastName": "Gadde" }, { "creatorType": "author", "firstName": "L. V.", "lastName": "Subramaniam" }, { "creatorType": "author", "firstName": "Tanveer A.", "lastName": "Faruquie" } ], "abstractNote": "With the increase in the number of people communicating through internet, there has been a steady increase in the amount of text available online. Most such text is different from the standard language, as people try to use various kinds of short forms for words to save time and effort. We call that noisy text. Part-Of-Speech (POS) tagging has reached high levels of accuracy enabling the use of automatic POS tags in various language processing tasks, however, tagging performance on noisy text degrades very fast. This paper is an attempt to adapt a state-of-the-art English POS tagger, which is trained on the Wall-Street-Journal (WSJ) corpus, to noisy text. We classify the noise in text into different types and evaluate the tagger with respect to each type of noise. The problem of tagging noisy text is attacked in two ways; a) Trying to overcome noise as a post processing step to the tagging b) Cleaning the noise and then doing tagging. We propose techniques to solve the problem in both the ways and critically compare them based on the error analysis. We demonstrate the working of the proposed models on a Short Message Service (SMS) dataset which achieve a significant improvement over the baseline accuracy of tagging noisy words by a state-of-the-art English POS tagger.", "proceedingsTitle": "Proceedings of the 2011 Joint Workshop on Multilingual OCR and Analytics for Noisy Unstructured Text Data", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2011", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "5:1–5:8", "series": "MOCR_AND '11", "seriesNumber": "", "DOI": "10.1145/2034617.2034623", "ISBN": "978-1-4503-0685-0", "citationKey": "", "url": "http://doi.acm.org/10.1145/2034617.2034623", "accessDate": "2015-02-20T23:20:25Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Adapting a WSJ Trained Part-of-speech Tagger to Noisy Text", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "NLP", "type": 1 }, { "tag": "POS tagging", "type": 1 }, { "tag": "adapting", "type": 1 }, { "tag": "natural language processing", "type": 1 }, { "tag": "noisy text", "type": 1 }, { "tag": "noisy text analytics", "type": 1 }, { "tag": "part-of-speech", "type": 1 }, { "tag": "robust towards noise", "type": 1 } ], "collections": [ "FW9Q2H2W", "QZBMSSWC" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/59CFNRKV" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "XBVSETBM", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/XBVSETBM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/XBVSETBM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Jiang et al.", "parsedDate": "2011", "numChildren": 0 }, "data": { "key": "XBVSETBM", "version": 2, "itemType": "conferencePaper", "title": "Target-dependent Twitter Sentiment Classification", "creators": [ { "creatorType": "author", "firstName": "Long", "lastName": "Jiang" }, { "creatorType": "author", "firstName": "Mo", "lastName": "Yu" }, { "creatorType": "author", "firstName": "Ming", "lastName": "Zhou" }, { "creatorType": "author", "firstName": "Xiaohua", "lastName": "Liu" }, { "creatorType": "author", "firstName": "Tiejun", "lastName": "Zhao" } ], "abstractNote": "Sentiment analysis on Twitter data has attracted much attention recently. In this paper, we focus on target-dependent Twitter sentiment classification; namely, given a query, we classify the sentiments of the tweets as positive, negative or neutral according to whether they contain positive, negative or neutral sentiments about that query. Here the query serves as the target of the sentiments. The state-of-the-art approaches for solving this problem always adopt the target-independent strategy, which may assign irrelevant sentiments to the given target. Moreover, the state-of-the-art approaches only take the tweet to be classified into consideration when classifying the sentiment; they ignore its context (i.e., related tweets). However, because tweets are usually short and more ambiguous, sometimes it is not enough to consider only the current tweet for sentiment classification. In this paper, we propose to improve target-dependent Twitter sentiment classification by 1) incorporating target-dependent features; and 2) taking related tweets into consideration. According to the experimental results, our approach greatly improves the performance of target-dependent sentiment classification.", "proceedingsTitle": "Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Stroudsburg, PA, USA", "date": "2011", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "151–160", "series": "HLT '11", "seriesNumber": "", "DOI": "", "ISBN": "978-1-932432-87-9", "citationKey": "", "url": "http://dl.acm.org/citation.cfm?id=2002472.2002492", "accessDate": "2015-02-20T23:05:50Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "FW9Q2H2W", "QZBMSSWC" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/4G8HJVK5" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "AQ6S7SJT", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/AQ6S7SJT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/AQ6S7SJT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Jung", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "AQ6S7SJT", "version": 2, "itemType": "journalArticle", "title": "Online named entity recognition method for microtexts in social networking services: A case study of twitter", "creators": [ { "creatorType": "author", "firstName": "Jason J.", "lastName": "Jung" } ], "abstractNote": "", "publicationTitle": "Expert Systems with Applications", "publisher": "", "place": "", "date": "2012", "volume": "39", "issue": "9", "section": "", "partNumber": "", "partTitle": "", "pages": "8066–8070", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://www.sciencedirect.com/science/article/pii/S0957417412001546", "accessDate": "2015-02-23T18:18:14Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Online named entity recognition method for microtexts in social networking services", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "7MV5T9KF" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/4SUSR3CQ" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "T2C4RSVR", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/T2C4RSVR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/T2C4RSVR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Li et al.", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "T2C4RSVR", "version": 2, "itemType": "conferencePaper", "title": "TwiNER: Named Entity Recognition in Targeted Twitter Stream", "creators": [ { "creatorType": "author", "firstName": "Chenliang", "lastName": "Li" }, { "creatorType": "author", "firstName": "Jianshu", "lastName": "Weng" }, { "creatorType": "author", "firstName": "Qi", "lastName": "He" }, { "creatorType": "author", "firstName": "Yuxia", "lastName": "Yao" }, { "creatorType": "author", "firstName": "Anwitaman", "lastName": "Datta" }, { "creatorType": "author", "firstName": "Aixin", "lastName": "Sun" }, { "creatorType": "author", "firstName": "Bu-Sung", "lastName": "Lee" } ], "abstractNote": "Many private and/or public organizations have been reported to create and monitor targeted Twitter streams to collect and understand users' opinions about the organizations. Targeted Twitter stream is usually constructed by filtering tweets with user-defined selection criteria e.g. tweets published by users from a selected region, or tweets that match one or more predefined keywords. Targeted Twitter stream is then monitored to collect and understand users' opinions about the organizations. There is an emerging need for early crisis detection and response with such target stream. Such applications require a good named entity recognition (NER) system for Twitter, which is able to automatically discover emerging named entities that is potentially linked to the crisis. In this paper, we present a novel 2-step unsupervised NER system for targeted Twitter stream, called TwiNER. In the first step, it leverages on the global context obtained from Wikipedia and Web N-Gram corpus to partition tweets into valid segments (phrases) using a dynamic programming algorithm. Each such tweet segment is a candidate named entity. It is observed that the named entities in the targeted stream usually exhibit a gregarious property, due to the way the targeted stream is constructed. In the second step, TwiNER constructs a random walk model to exploit the gregarious property in the local context derived from the Twitter stream. The highly-ranked segments have a higher chance of being true named entities. We evaluated TwiNER on two sets of real-life tweets simulating two targeted streams. Evaluated using labeled ground truth, TwiNER achieves comparable performance as with conventional approaches in both streams. Various settings of TwiNER have also been examined to verify our global context + local context combo idea.", "proceedingsTitle": "Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2012", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "721–730", "series": "SIGIR '12", "seriesNumber": "", "DOI": "10.1145/2348283.2348380", "ISBN": "978-1-4503-1472-5", "citationKey": "", "url": "http://doi.acm.org/10.1145/2348283.2348380", "accessDate": "2015-02-23T18:16:09Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "TwiNER", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Twitter", "type": 1 }, { "tag": "named entity recognition", "type": 1 }, { "tag": "tweets", "type": 1 }, { "tag": "web n-gram", "type": 1 }, { "tag": "wikipedia", "type": 1 } ], "collections": [ "7MV5T9KF" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/HW3ESPZ2" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "JVFH5E2S", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/JVFH5E2S", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/JVFH5E2S", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/331416/items/VIUSS5AI", "type": "application/json" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "JVFH5E2S", "version": 2, "parentItem": "VIUSS5AI", "itemType": "note", "note": "
One more trained method
", "tags": [], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/TB6RR2WR" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "HCM9EN9G", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/HCM9EN9G", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/HCM9EN9G", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/331416/items/FCGH63WP", "type": "application/json" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "HCM9EN9G", "version": 2, "parentItem": "FCGH63WP", "itemType": "note", "note": "NER also involves Named-Entity Normalization (NEN).
\nA particular challenge in tweets because errors can propagate.
\n\n
Graphical model for NEN/NER
", "tags": [], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/A3CKJ25N" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "DA53QE5T", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/DA53QE5T", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/DA53QE5T", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Qin", "parsedDate": "2015-01-07", "numChildren": 0 }, "data": { "key": "DA53QE5T", "version": 2, "itemType": "journalArticle", "title": "Hero on Twitter, Traitor on News How Social Media and Legacy News Frame Snowden", "creators": [ { "creatorType": "author", "firstName": "Jie", "lastName": "Qin" } ], "abstractNote": "Is Edward Snowden a hero or traitor? In what ways do frames on social media and legacy news differ in covering the incident of Edward Snowden? Utilizing the approach of semantic network analysis, the study found social media users associated Snowden’s case with other whistle-blowers, bipartisan issues, and personal privacy issues, while professional journalists associated the Snowden incident with issues of national security and international relations. Frames on social media portray Edward Snowden as a hero while the frames on legacy news make him a traitor. The study further identified media frames on social media and legacy news differ in two ways: word selection and word salience. In addition, the study discussed the challenges and opportunities of framing analysis in the context of social media.", "publicationTitle": "The International Journal of Press/Politics", "publisher": "", "place": "", "date": "2015-01-07", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "1940161214566709", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "The International Journal of Press/Politics", "DOI": "10.1177/1940161214566709", "citationKey": "", "url": "http://hij.sagepub.com/content/early/2015/01/06/1940161214566709", "accessDate": "2015-02-23T18:49:36Z", "PMID": "", "PMCID": "", "ISSN": "1940-1612, 1940-1620", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "hij.sagepub.com", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "framing theory", "type": 1 }, { "tag": "legacy news", "type": 1 }, { "tag": "public opinion", "type": 1 }, { "tag": "semantic network", "type": 1 }, { "tag": "social media", "type": 1 } ], "collections": [ "BIPVITQQ" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/HAK2QXJ5" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "ACP45B39", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/ACP45B39", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/ACP45B39", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "HIZUKA et al.", "parsedDate": "2007", "numChildren": 0 }, "data": { "key": "ACP45B39", "version": 2, "itemType": "journalArticle", "title": "Semantic Role Labeling based on Japanese FrameNet", "creators": [ { "creatorType": "author", "firstName": "SHINSUKE", "lastName": "HIZUKA" }, { "creatorType": "author", "firstName": "HIROYUKI", "lastName": "OKAMOTO" }, { "creatorType": "author", "firstName": "HIROAKI", "lastName": "SAITO" }, { "creatorType": "author", "firstName": "KYOKOHIROSE", "lastName": "OHARA" } ], "abstractNote": "This paper proposes a stochastic model for semantic role labeling based on Japanese FrameNet and suggests a method to acquire it by machine learning. The model distinguishes semantic roles which cannot be separated by surface cases. The model receives a sentence and its predicate, identifies its predicate argument structure, then identifies the arguments to be labeled, and finally labels them with adequate semantic roles. The system based on the model achieved 77% precision and 68% recall in identifying the semantic roles of the pre-segmented arguments under the condition that the system labels the role whose certainty is more than the threshold. For more difficult tasks of identifying the arguments which should be labeled and their roles, the system attained 63% precision and 43% recall under the same condition. The system also achieved to label different semantic roles to the arguments whose surface cases are identical.", "publicationTitle": "Journal of Natural Language Processing", "publisher": "", "place": "", "date": "2007", "volume": "14", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "43-66", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.5715/jnlp.14.43", "citationKey": "", "url": "http://ci.nii.ac.jp/naid/130004291900/", "accessDate": "2015-02-23T18:35:19Z", "PMID": "", "PMCID": "", "ISSN": "1340-7619", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "CiNii", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Maximum entropy method", "type": 1 }, { "tag": "Semantic role labeling", "type": 1 }, { "tag": "Support vector machine", "type": 1 } ], "collections": [ "BIPVITQQ" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/BJZE5C4M" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "CEEDQXRJ", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/CEEDQXRJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/CEEDQXRJ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "creatorSummary": "Kase", "parsedDate": "2013-06", "numChildren": 0 }, "data": { "key": "CEEDQXRJ", "version": 2, "itemType": "report", "title": "Accelerating Exploitation of Low-grade Intelligence through Semantic Text Processing of Social Media", "creators": [ { "creatorType": "author", "firstName": "Sue E.", "lastName": "Kase" } ], "abstractNote": "Social media will play a key role in many areas of intelligence operations with the development of knowledge extraction analytics. The data contained within these social networking services present many challenges, but the value obtained from detecting subtle and hidden information exchanges and environmental observations are vast. The analytics that will drive social media knowledge exploitation include advanced text processing technologies allowing multi-faceted concept or frame-based queries within a familiar search engine interface for users who are not expert analysts or who may be operating with limited intelligence resources in disadvantaged information collection situations. In this paper, we demonstrate constructing frame-based semantic search queries using models of concepts and roles extracted from social media content. This approach to searching allows intuitive query formulations requiring less up-front knowledge of the search parameters. We demonstrate this semantic search capability by querying over seven million tweets captured during the Arab Spring uprisings.", "reportNumber": "", "reportType": "", "institution": "", "place": "", "date": "2013-06", "seriesTitle": "", "seriesNumber": "", "pages": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Defense Technical Information Center", "callNumber": "", "rights": "Approved for public release; distribution is unlimited.", "extra": "", "tags": [ { "tag": "*EGYPT UPRISINGS", "type": 1 }, { "tag": "*INFORMATION RETRIEVAL", "type": 1 }, { "tag": "*INTELLIGENCE", "type": 1 }, { "tag": "*INTELLIGENCE EXPLOITATION", "type": 1 }, { "tag": "*INTERNET", "type": 1 }, { "tag": "*ONLINE COMMUNITIES", "type": 1 }, { "tag": "*POLITICAL REVOLUTION", "type": 1 }, { "tag": "*SEMANTIC TEXT PROCESSING", "type": 1 }, { "tag": "*SEMANTICS", "type": 1 }, { "tag": "*SOCIAL MEDIA", "type": 1 }, { "tag": "*TEXT PROCESSING", "type": 1 }, { "tag": "ADVANCED ANALYTICS", "type": 1 }, { "tag": "ARAB SPRING TWEETS", "type": 1 }, { "tag": "ARAB SPRING UPRISINGS", "type": 1 }, { "tag": "BRIEFING CHARTS", "type": 1 }, { "tag": "CONTOUR", "type": 1 }, { "tag": "Computer Systems", "type": 1 }, { "tag": "EGYPT", "type": 1 }, { "tag": "EXTRACTION", "type": 1 }, { "tag": "FRAME-BASED SEMANTIC SEARCH QUERIES", "type": 1 }, { "tag": "FRAMENET-BASED SEMANTIC SEARCHING", "type": 1 }, { "tag": "GOVERNMENT(FOREIGN)", "type": 1 }, { "tag": "Government and Political Science", "type": 1 }, { "tag": "INTERACTIONS", "type": 1 }, { "tag": "INTERPERSONAL RELATIONS", "type": 1 }, { "tag": "Information Science", "type": 1 }, { "tag": "KNOWLEDGE EXPLOITATION", "type": 1 }, { "tag": "LOW-GRADE INTELLIGENCE", "type": 1 }, { "tag": "Linguistics", "type": 1 }, { "tag": "Psychology", "type": 1 }, { "tag": "ROLES(BEHAVIOR)", "type": 1 }, { "tag": "SOCIAL NETWORKS", "type": 1 }, { "tag": "SYMPOSIA", "type": 1 }, { "tag": "TAHRIR SQUARE(EGYPT)", "type": 1 }, { "tag": "Twitter", "type": 1 }, { "tag": "WORDS(LANGUAGE)", "type": 1 }, { "tag": "information extraction", "type": 1 }, { "tag": "situational awareness", "type": 1 } ], "collections": [ "BIPVITQQ" ], "relations": { "owl:sameAs": "http://zotero.org/groups/270765/items/DVQ4RCJ9" }, "dateAdded": "2015-02-25T00:16:48Z", "dateModified": "2015-02-25T00:16:48Z" } }, { "key": "GAQJNJ7B", "version": 2, "library": { "type": "group", "id": 331416, "name": "UCLA Newscape Team", "links": { "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/331416/items/GAQJNJ7B", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ucla_newscape_team/items/GAQJNJ7B", "type": "text/html" } }, "meta": { "createdByUser": { "id": 20034, "username": "dshepard", "name": "Dave Shepard", "links": { "alternate": { "href": "https://www.zotero.org/dshepard", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "GAQJNJ7B", "version": 2, "itemType": "note", "note": "POS Tagging approaches on Tweets
\nStandard NLP tools don't work well. POS tagging accuracy drops from 97% to 80% on tweets. (Ritter 1525)
\nProblems:
\n