[ { "key": "UC5H7WJV", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/UC5H7WJV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/UC5H7WJV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 648812, "username": "bronwenjm", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/bronwenjm", "type": "text/html" } } }, "lastModifiedByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Flanders and Fraistat", "parsedDate": "2013", "numChildren": 1 }, "data": { "key": "UC5H7WJV", "version": 8320, "itemType": "book", "title": "The Cambridge Companion to Textual Scholarship", "creators": [ { "creatorType": "editor", "firstName": "Julia", "lastName": "Flanders" }, { "creatorType": "editor", "firstName": "Neil", "lastName": "Fraistat" } ], "abstractNote": "", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2013", "publisher": "Cambridge University Press", "place": "Cambridge", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "1", "ISBN": "978-0-521-51410-1", "DOI": "", "citationKey": "flandCambr2013", "url": "http://dx.doi.org/10.1017/CCO9781139044073", "accessDate": "2014-03-11T19:44:57Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "search.library.wisc.edu", "callNumber": "Use Internet link(s) in this record", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2014-03-11T19:44:57Z", "dateModified": "2014-03-11T19:44:57Z" } }, { "key": "DCQBGTDQ", "version": 8316, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/DCQBGTDQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/DCQBGTDQ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/420/items/UC5H7WJV", "type": "application/json" } }, "meta": { "createdByUser": { "id": 648812, "username": "bronwenjm", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/bronwenjm", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "DCQBGTDQ", "version": 8316, "parentItem": "UC5H7WJV", "itemType": "note", "note": "Title from publishers bibliographic system (viewed on 05 Jun 2013)", "tags": [], "relations": {}, "dateAdded": "2014-03-11T19:44:57Z", "dateModified": "2014-03-11T19:44:57Z" } }, { "key": "U5UUKPEC", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/U5UUKPEC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/U5UUKPEC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 648812, "username": "bronwenjm", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/bronwenjm", "type": "text/html" } } }, "lastModifiedByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Galey", "parsedDate": "2012", "numChildren": 0 }, "data": { "key": "U5UUKPEC", "version": 8320, "itemType": "journalArticle", "title": "The Enkindling Reciter: E-Books in the Bibliographical Imagination", "creators": [ { "creatorType": "author", "firstName": "Alan", "lastName": "Galey" } ], "abstractNote": "", "publicationTitle": "Book History Book History", "publisher": "", "place": "", "date": "2012", "volume": "15", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "210-247", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "galeyEnkin2012", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "The Enkindling Reciter", "language": "English", "libraryCatalog": "Open WorldCat", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Book Studies", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2014-03-11T19:29:03Z", "dateModified": "2014-03-11T19:29:03Z" } }, { "key": "SJFET87R", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/SJFET87R", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/SJFET87R", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Romero et al.", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "SJFET87R", "version": 8320, "itemType": "conferencePaper", "title": "Automatic extraction of the main terminology used in empirical software engineering through text mining techniques", "creators": [ { "creatorType": "author", "firstName": "Francisco P.", "lastName": "Romero" }, { "creatorType": "author", "firstName": "José A.", "lastName": "Olivas" }, { "creatorType": "author", "firstName": "Marcela", "lastName": "Genero" }, { "creatorType": "author", "firstName": "Mario", "lastName": "Piattini" } ], "abstractNote": "The need for an explicit common terminology within Empirical Software Engineering (an ESE-Glossary of terms) was highlighted in the ISERN 2007 meeting [2]. The goal was to define a glossary of terms related to ESE based on an initial glossary published in http://lens-ese.cos.ufrj.br/wikiese. This initial glossary was built manually, based on expert knowledge. However, owing to the dynamic nature of the research works in ESE, this glossary must be dynamically updated with information extracted from the relevant documents in the research domain. Automation is, therefore, mandatory. We propose a text mining technique for the automatic extraction of the most relevant terms used in ESE documents. Our technique also provides the relationships between terms, with the degree of affinity between them. Our approach could, therefore, be useful in the improvement of the initial glossary of terms and in discovering relationships between terms.", "proceedingsTitle": "Proceedings of the Second ACM-IEEE international symposium on Empirical software engineering and measurement", "conferenceName": "", "publisher": "ACM", "place": "Kaiserslautern, Germany", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "357-358", "series": "", "seriesNumber": "", "DOI": "10.1145/1414004.1414082", "ISBN": "978-1-59593-971-5", "citationKey": "romerAutom2008", "url": "http://portal.acm.org/citation.cfm?id=1414004.1414082&coll=portal&dl=GUIDE&CFID=39731654&CFTOKEN=77798259", "accessDate": "2009-06-19T08:51:44Z", "ISSN": "", "archive": "ACM", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "glossary", "type": 1 }, { "tag": "ontologies", "type": 1 }, { "tag": "text mining", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2009-07-05T18:59:10Z", "dateModified": "2010-06-12T15:50:46Z" } }, { "key": "S7QWMG7P", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/S7QWMG7P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/S7QWMG7P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "S7QWMG7P", "version": 8320, "itemType": "computerProgram", "title": "The Protégé Ontology Editor and Knowledge Acquisition System", "creators": [], "abstractNote": "", "seriesTitle": "", "versionNumber": "", "date": "", "system": "", "company": "", "place": "", "programmingLanguage": "", "rights": "", "citationKey": "Prote", "url": "http://protege.stanford.edu/", "accessDate": "2009-01-05T13:55:49Z", "DOI": "", "ISBN": "", "archive": "", "archiveLocation": "", "libraryCatalog": "", "callNumber": "0000", "shortTitle": "", "extra": "", "tags": [ { "tag": "Manual" }, { "tag": "Ontologien" }, { "tag": "Reasoning" } ], "collections": [], "relations": {}, "dateAdded": "2009-06-09T20:21:44Z", "dateModified": "2010-06-12T15:50:45Z" } }, { "key": "RDEAXHWB", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/RDEAXHWB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/RDEAXHWB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Lee and Yang", "parsedDate": "2003", "numChildren": 0 }, "data": { "key": "RDEAXHWB", "version": 8320, "itemType": "journalArticle", "title": "A Multilingual Text Mining Approach Based on Self-Organizing Maps", "creators": [ { "creatorType": "author", "firstName": "Chung-Hong", "lastName": "Lee" }, { "creatorType": "author", "firstName": "Hsin-Chang", "lastName": "Yang" } ], "abstractNote": "This paper describes our work on developing a language-independent technique for discovery of implicit knowledge from multilingual information sources. Text mining has been gaining popularity in the knowledge discovery field, particularity with the increasing availability of digital documents in various languages from all around the world. However, currently most text mining tools mainly focus only on processing monolingual documents (particularly English documents): little attention has been paid to apply the techniques to handle the documents in Asian languages, and further extend the mining algorithms to support the aspects of multilingual information sources. In this work, we attempt to develop a language-neutral method to tackle the linguistics difficulties in the text mining process. Using a variation of automatic clustering techniques, which apply a neural net approach, namely the Self-Organizing Maps (SOM), we have conducted several experiments to uncover associated documents based on a Chinese corpus, Chinese-English bilingual parallel corpora, and a hybrid Chinese-English corpus. The experiments show some interesting results and a couple of potential paths for future work in the field of multilingual information discovery. Besides, this work is expected to act as a starting point for exploring the impacts on linguistics issues with the machine-learning approach to mining sensible linguistics elements from multilingual text collections.", "publicationTitle": "Applied Intelligence", "publisher": "", "place": "", "date": "2003", "volume": "18", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "295-310", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "leeMulti2003", "url": "http://portal.acm.org/citation.cfm?id=762622.762655&coll=portal&dl=GUIDE&CFID=39731654&CFTOKEN=77798259", "accessDate": "2009-06-19T08:51:58Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "information retrieval", "type": 1 }, { "tag": "knowledge extraction", "type": 1 }, { "tag": "multilingual text mining", "type": 1 }, { "tag": "self-organizing maps", "type": 1 }, { "tag": "web mining", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2009-07-05T19:00:46Z", "dateModified": "2010-06-12T15:50:44Z" } }, { "key": "JEAZATT6", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/JEAZATT6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/JEAZATT6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Baca", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "JEAZATT6", "version": 8320, "itemType": "book", "title": "Introduction to metadata", "creators": [ { "creatorType": "author", "firstName": "Murtha", "lastName": "Baca" } ], "abstractNote": "", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2008", "publisher": "", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "VI, 80 S.", "ISBN": "", "DOI": "", "citationKey": "bacaIntro2008", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "Definition" }, { "tag": "Metadaten" }, { "tag": "Metadaten-Arten" }, { "tag": "q27" } ], "collections": [], "relations": {}, "dateAdded": "2009-06-09T20:20:03Z", "dateModified": "2010-06-12T15:50:43Z" } }, { "key": "IU4BT242", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/IU4BT242", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/IU4BT242", "type": "text/html" } }, "meta": { "createdByUser": { "id": 34927, "username": "alsarhan", "name": "Hesham Alsarhan", "links": { "alternate": { "href": "https://www.zotero.org/alsarhan", "type": "text/html" } } }, "lastModifiedByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Bojārs et al.", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "IU4BT242", "version": 8320, "itemType": "journalArticle", "title": "Interlinking the Social Web with Semantics", "creators": [ { "creatorType": "author", "firstName": "Uldis", "lastName": "Bojārs" }, { "creatorType": "author", "firstName": "John G.", "lastName": "Breslin" }, { "creatorType": "author", "firstName": "Vassilios", "lastName": "Peristeras" }, { "creatorType": "author", "firstName": "Giovanni", "lastName": "Tummarello" }, { "creatorType": "author", "firstName": "Stefan", "lastName": "Decker" } ], "abstractNote": "One of the most visible trends on the Web is the emergence of Social Web sites, which help people create and gather knowledge by simplifying user contributions via blogs, tagging and folksonomies, wikis, podcasts, and online social networks. Current online-community sites are isolated from one another, like islands in a sea. Various discussions might contain complementary knowledge and discussions—parts of the answer a person is looking for—but people participating in one discussion can't readily access information about related discussions elsewhere. The potential synergies among many sites, communities, and services are expensive to exploit, and their data are difficult and cumbersome to link and reuse. The main reason for this lack of interoperation is that for the most part in the Social Web, common standards still don't exist for knowledge and information exchange and interoperation. However, the Semantic Web effort aims to provide the tools needed to define extensible, flexible standards for this purpose. The Semantic Web technology stack is well defined, enabling the creation of metadata and associated vocabularies. The Semantic Web effort is in an ideal position to make Social Web sites interoperable. Applying Semantic Web frameworks including SIOC (Semantically Interlinked Online Communities) and FOAF (Friend-of-a-Friend) to the Social Web can lead to a Social Semantic Web, creating a network of interlinked and semantically rich knowledge. This article is part of a special issue called Semantic Web Update.", "publicationTitle": "IEEE Intelligent Systems", "publisher": "", "place": "", "date": "2008", "volume": "23", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "29-40", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "bojarInter2008", "url": "http://portal.acm.org/citation.cfm?id=1373102.1373153", "accessDate": "2009-06-05T03:18:22Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "enterprise applications", "type": 1 }, { "tag": "foaf", "type": 1 }, { "tag": "ontologies", "type": 1 }, { "tag": "semantic technologies", "type": 1 }, { "tag": "semantic web", "type": 1 }, { "tag": "sioc", "type": 1 }, { "tag": "social media", "type": 1 }, { "tag": "social software", "type": 1 }, { "tag": "social web", "type": 1 }, { "tag": "the web", "type": 1 }, { "tag": "web 2.0", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2009-07-23T00:31:44Z", "dateModified": "2010-06-12T15:50:42Z" } }, { "key": "CICFNW7D", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/CICFNW7D", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/CICFNW7D", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Ingvaldsen et al.", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "CICFNW7D", "version": 8320, "itemType": "conferencePaper", "title": "Financial News Mining: Monitoring Continuous Streams of Text", "creators": [ { "creatorType": "author", "firstName": "Jon Espen", "lastName": "Ingvaldsen" }, { "creatorType": "author", "firstName": "Jon Atle", "lastName": "Gulla" }, { "creatorType": "author", "firstName": "Tarjei", "lastName": "Laegreid" }, { "creatorType": "author", "firstName": "Paul Christian", "lastName": "Sandal" } ], "abstractNote": "This paper addresses the problem of extracting, analyzing and synthesizing valuable information from continuous text streams covering financial information. A text mining framework combining elements from information retrieval, information extraction and natural language processing has been implemented. The framework is utilized to extract information regarding key actors in the domain, how they relate to each other, and how these characteristics evolve over time.", "proceedingsTitle": "Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence", "conferenceName": "", "publisher": "IEEE Computer Society", "place": "", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "321-324", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "0-7695-2747-7", "citationKey": "ingvaFinan2006", "url": "http://portal.acm.org/citation.cfm?id=1248823.1249127&coll=portal&dl=GUIDE&CFID=39731654&CFTOKEN=77798259", "accessDate": "2009-06-19T08:51:55Z", "ISSN": "", "archive": "ACM", "archiveLocation": "", "shortTitle": "Financial News Mining", "language": "", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-07-05T18:58:48Z", "dateModified": "2010-06-12T15:50:41Z" } }, { "key": "AWS86BUW", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/AWS86BUW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/AWS86BUW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Suhara et al.", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "AWS86BUW", "version": 8320, "itemType": "conferencePaper", "title": "Extracting related named entities from blogosphere for event mining", "creators": [ { "creatorType": "author", "firstName": "Yoshihiko", "lastName": "Suhara" }, { "creatorType": "author", "firstName": "Hiroyuki", "lastName": "Toda" }, { "creatorType": "author", "firstName": "Akito", "lastName": "Sakurai" } ], "abstractNote": "We propose a method of extracting named entities that are related to a single input word. Focusing on the syntactic dependency relation in sentences, it is reasonable to extract a case element that syntactically depends on the predicate that the input word depends on. In Japanese, though, a word which has appeared in a previous sentence is often omitted or replaced. Our proposed method, first, extracts \"predicate patterns\" consisting of case elements with case particles and a predicate. Then it combines predicate patterns that have the same predicate to form possible unabridged dependence relations.", "proceedingsTitle": "Proceedings of the 2nd international conference on Ubiquitous information management and communication", "conferenceName": "", "publisher": "ACM", "place": "Suwon, Korea", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "225-229", "series": "", "seriesNumber": "", "DOI": "10.1145/1352793.1352841", "ISBN": "978-1-59593-993-7", "citationKey": "suharExtra2008", "url": "http://portal.acm.org/citation.cfm?id=1352793.1352841&coll=portal&dl=GUIDE&CFID=39731654&CFTOKEN=77798259", "accessDate": "2009-06-19T08:51:49Z", "ISSN": "", "archive": "ACM", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "information extraction", "type": 1 }, { "tag": "text mining", "type": 1 }, { "tag": "world wide web", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2009-07-05T18:58:44Z", "dateModified": "2010-06-12T15:50:40Z" } }, { "key": "865UEVZ9", "version": 8320, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/865UEVZ9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/865UEVZ9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Myung et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "865UEVZ9", "version": 8320, "itemType": "conferencePaper", "title": "PicAChoo: a tool for customizable feature extraction utilizing characteristics of textual data", "creators": [ { "creatorType": "author", "firstName": "Jaeseok", "lastName": "Myung" }, { "creatorType": "author", "firstName": "Jung-Yeon", "lastName": "Yang" }, { "creatorType": "author", "firstName": "Sang-goo", "lastName": "Lee" } ], "abstractNote": "Although documents have hundreds of thousands of unique words, only a small number of words are significantly useful for intelligent services. For this reason, feature extraction has become an important issue to be addressed in various fields, such as information retrieval, text mining, pattern recognition, etc. Numerous supporting tools for feature extraction are available, but most of them deal with text as a simple literal. Unfortunately, text is not just a literal, but a semantically significant unit including linguistic characteristics. So, we need customized extraction methods that consider the characteristics of source documents. PicAChoo stands for 'Pick And Choose', and it provides an environment which enables feature extraction methods using the structure of sentences and the part-of-speech information of words. Moreover, we suggest dynamic composition of different extraction methods without hard-coding.", "proceedingsTitle": "Proceedings of the 3rd International Conference on Ubiquitous Information Management and Communication", "conferenceName": "", "publisher": "ACM", "place": "Suwon, Korea", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "650-655", "series": "", "seriesNumber": "", "DOI": "10.1145/1516241.1516356", "ISBN": "978-1-60558-405-8", "citationKey": "myungPicAC2009", "url": "http://portal.acm.org/citation.cfm?id=1516241.1516356&coll=portal&dl=GUIDE&CFID=39731654&CFTOKEN=77798259", "accessDate": "2009-06-19T08:51:38Z", "ISSN": "", "archive": "ACM", "archiveLocation": "", "shortTitle": "PicAChoo", "language": "", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "complex feature", "type": 1 }, { "tag": "customizable feature extraction", "type": 1 }, { "tag": "feature storing model", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2009-07-05T18:58:09Z", "dateModified": "2010-06-12T15:50:39Z" } }, { "key": "77KXS97K", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/77KXS97K", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/77KXS97K", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Joachims", "numChildren": 0 }, "data": { "key": "77KXS97K", "version": 8321, "itemType": "conferencePaper", "title": "Text categorization with support vector machines: learning with many relevant features (application/pdf-Objekt)", "creators": [ { "creatorType": "author", "firstName": "Thorsten", "lastName": "Joachims" } ], "abstractNote": "This paper introduces support vector machines for text categorization. It provides both theoretical and empirical evidence that SVMs are very well suited for text categorization. The theoretical analysis concludes that SVMs acknowledge\n\nthe particular properties of text a) high dimensional feature spaces b) few irrelevant features dense concept vector and c) sparse instance vectors.The experimental results show that SVMs consistently achieve good performance on text categorization tasks outperforming existing methods substantially and signicantly With their ability to generalize well in high dimensional\n\nfeature spaces SVMs eliminate the need for feature selection making the application of text categorization considerably easier Another advantage of SVMs over the conventional methods is their robustness. SVMs show good performance in all experiments avoiding catastrophic failure as observed with the conventional methods on some tasks Furthermore SVMs do not require any parameter tuning since they can and good parameter settings automatically All this makes SVMs a very promising and easy to use method for learning text classiers from examples.", "proceedingsTitle": "", "conferenceName": "", "publisher": "", "place": "", "date": "", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "joachText", "url": "http://www.cs.cornell.edu/People/tj/publications/joachims_98a.pdf", "accessDate": "2009-01-14T18:41:03Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "Algorithmus" }, { "tag": "Automatische Klassifikation" }, { "tag": "Experimente" }, { "tag": "Klassifizierung" }, { "tag": "Maschninelles Lernen" }, { "tag": "Textanalyse" }, { "tag": "Vektorbasiert" } ], "collections": [], "relations": {}, "dateAdded": "2009-07-05T18:57:04Z", "dateModified": "2010-06-12T15:50:38Z" } }, { "key": "5S98GAJN", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/5S98GAJN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/5S98GAJN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "5S98GAJN", "version": 8321, "itemType": "computerProgram", "title": "GATE, A General Architecture for Text Engineering", "creators": [], "abstractNote": "", "seriesTitle": "", "versionNumber": "", "date": "", "system": "", "company": "", "place": "", "programmingLanguage": "", "rights": "", "citationKey": "GATE", "url": "http://gate.ac.uk/", "accessDate": "2009-01-05T08:24:32Z", "DOI": "", "ISBN": "", "archive": "", "archiveLocation": "", "libraryCatalog": "", "callNumber": "0000", "shortTitle": "", "extra": "", "tags": [ { "tag": "Information Extraction" }, { "tag": "Textanalyse" }, { "tag": "java" }, { "tag": "open source" } ], "collections": [], "relations": {}, "dateAdded": "2009-06-09T20:21:29Z", "dateModified": "2010-06-12T15:50:37Z" } }, { "key": "3QKEC3IB", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/3QKEC3IB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/3QKEC3IB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 32490, "username": "damiano", "name": "Damiano Spina", "links": { "alternate": { "href": "https://www.zotero.org/damiano", "type": "text/html" } } }, "lastModifiedByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Heinrich", "parsedDate": "2005", "numChildren": 0 }, "data": { "key": "3QKEC3IB", "version": 8321, "itemType": "journalArticle", "title": "Parameter estimation for text analysis", "creators": [ { "creatorType": "author", "firstName": "G.", "lastName": "Heinrich" } ], "abstractNote": "", "publicationTitle": "Web: http://www. arbylon. net/publications/text-est. pdf", "publisher": "", "place": "", "date": "2005", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "heinrParam2005", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-10-23T08:55:49Z", "dateModified": "2010-06-12T15:50:36Z" } }, { "key": "3IZFCAZ2", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/3IZFCAZ2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/3IZFCAZ2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Atkinson and Goot", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "3IZFCAZ2", "version": 8321, "itemType": "conferencePaper", "title": "Near real time information mining in multilingual news", "creators": [ { "creatorType": "author", "firstName": "Martin", "lastName": "Atkinson" }, { "creatorType": "author", "firstName": "Erik Van der", "lastName": "Goot" } ], "abstractNote": "This paper presents a near real-time multilingual news monitoring and analysis system that forms the backbone of our research work. The system integrates technologies to address the problems related to information extraction and analysis of open source intelligence on the World Wide Web. By chaining together different techniques in text mining, automated machine learning and statistical analysis, we can automatically determine who, where and, to a certain extent, what is being reported in news articles.", "proceedingsTitle": "Proceedings of the 18th international conference on World wide web", "conferenceName": "", "publisher": "ACM", "place": "Madrid, Spain", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1153-1154", "series": "", "seriesNumber": "", "DOI": "10.1145/1526709.1526903", "ISBN": "978-1-60558-487-4", "citationKey": "atkinreal2009", "url": "http://portal.acm.org/citation.cfm?id=1526709.1526903&coll=portal&dl=GUIDE&CFID=39731654&CFTOKEN=77798259", "accessDate": "2009-06-19T08:51:33Z", "ISSN": "", "archive": "ACM", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "0000", "rights": "", "extra": "", "tags": [ { "tag": "automated media monitoring", "type": 1 }, { "tag": "information mining and analysis", "type": 1 }, { "tag": "multi-linguality", "type": 1 }, { "tag": "open source text", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2009-07-05T18:59:15Z", "dateModified": "2010-06-12T15:50:35Z" } }, { "key": "3PITBD6V", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/3PITBD6V", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/3PITBD6V", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Röser", "numChildren": 0 }, "data": { "key": "3PITBD6V", "version": 8321, "itemType": "webpage", "title": "Ein Vorgehensmodell zur operativen Erstellung von Metadaten", "creators": [ { "creatorType": "author", "firstName": "Marc", "lastName": "Röser" } ], "abstractNote": "", "websiteTitle": "Amazon", "websiteType": "Marketplace", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "roeserVorge", "url": "http://www.amazon.de/Ein-Vorgehensmodell-operativen-Erstellung-Metadaten/dp/3832515321/ref=sr_11_1?ie=UTF8&qid=1235132943&sr=11-1", "accessDate": "2009-02-20T12:29:42Z", "shortTitle": "", "language": "de", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-06-09T20:20:10Z", "dateModified": "2009-06-09T20:28:06Z" } }, { "key": "J5RDW6MT", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/J5RDW6MT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/J5RDW6MT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "creatorSummary": "Helmbrecht-Schaar", "numChildren": 0 }, "data": { "key": "J5RDW6MT", "version": 8321, "itemType": "webpage", "title": "Entwicklung eines Verfahrens der automatischen Klassifizierung für Textdokumente aus dem Fachbereich Informatik mithilfe eines fachspezifischen Klassifikationssystems", "creators": [ { "creatorType": "author", "firstName": "", "lastName": "Helmbrecht-Schaar" } ], "abstractNote": "Beschreibt Vorgehen zur automatischen klassierung von Schriften aus der Informatik unter nutzung der ACM Klassifikation.", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "helmbEntwi", "url": "http://www.ib.hu-berlin.de/~kumlau/handreichungen/h200/", "accessDate": "2009-01-14T19:43:23Z", "shortTitle": "Thesis automatische Klassifizierung | HU Berlin", "language": "de", "rights": "", "extra": "", "tags": [ { "tag": "Automatische Klassifikation" }, { "tag": "Klassifizierung" }, { "tag": "Textanalyse" } ], "collections": [], "relations": {}, "dateAdded": "2009-06-09T20:26:51Z", "dateModified": "2009-06-09T20:26:51Z" } }, { "key": "872GK8I7", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/872GK8I7", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/872GK8I7", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "872GK8I7", "version": 8321, "itemType": "webpage", "title": "FUMSI - Automatic Classification: A Panel Discussion", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "FUMSI", "url": "http://web.fumsi.com/go/article/manage/3579", "accessDate": "2009-03-04T23:51:04Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [ { "tag": "BBC" }, { "tag": "Best Practice" }, { "tag": "Erfahrungen" }, { "tag": "Interview" }, { "tag": "Klassifikationen" }, { "tag": "Taxonomien" } ], "collections": [], "relations": {}, "dateAdded": "2009-06-09T20:21:08Z", "dateModified": "2009-06-09T20:21:08Z" } }, { "key": "HP39XTHA", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/HP39XTHA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/HP39XTHA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "HP39XTHA", "version": 8321, "itemType": "webpage", "title": "Europeana's semantic search engine", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "Europ", "url": "http://eculture.cs.vu.nl/europeana/session/search", "accessDate": "2009-01-25T13:05:36Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [ { "tag": "Bibliothek" }, { "tag": "Europeana" }, { "tag": "Kultur" }, { "tag": "Semantic Web" }, { "tag": "sparql" } ], "collections": [], "relations": {}, "dateAdded": "2009-06-09T20:20:41Z", "dateModified": "2009-06-09T20:20:41Z" } }, { "key": "4N4DREM6", "version": 8321, "library": { "type": "group", "id": 420, "name": "metadata, text-mining and semantics", "links": { "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/420/items/4N4DREM6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/metadata_text-mining_and_semantics/items/4N4DREM6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 24741, "username": "datentaste", "name": "Johannes", "links": { "alternate": { "href": "https://www.zotero.org/datentaste", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "4N4DREM6", "version": 8321, "itemType": "webpage", "title": "Was ist THESEUS | Das Theseus Programm", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "Was", "url": "http://theseus-programm.de/was-ist-theseus.html", "accessDate": "2009-01-13T10:13:15Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [ { "tag": "Bundesregierung" }, { "tag": "Forschungsprojekte" }, { "tag": "Semantic Web" } ], "collections": [], "relations": {}, "dateAdded": "2009-05-17T15:11:13Z", "dateModified": "2009-05-17T15:11:13Z" } } ]