04198nam 2200745 450 991082701230332120230807210957.01-61451-838-61-61451-995-110.1515/9781614518389(CKB)3360000000515429(EBL)1692487(SSID)ssj0001401685(PQKBManifestationID)12607356(PQKBTitleCode)TC0001401685(PQKBWorkID)11370800(PQKB)10109418(MiAaPQ)EBC1692487(DE-B1597)428363(OCoLC)898769824(DE-B1597)9781614518389(Au-PeEL)EBL1692487(CaPaEBR)ebr11006141(CaONFJC)MIL807310(EXLCZ)99336000000051542920150127h20152015 uy 0engur|nu---|u||utxtccrCoreference annotation, resolution and evaluation in Polish /Maciej Ogrodniczuk [and four others]Berlin, [Germany] :Walter de Gruyter, Inc.,2015.©20151 online resource (298 p.)Description based upon print version of record.1-61451-835-1 Includes bibliographical references.Front matter --Contents --Preface --1. Reference, anaphora, coreference --2. Polish coreference-related studies --3. Related work --4. Annotation models --5. Annotation guidelines --6. Annotation methodology --7. Annotation tools --8. Polish Coreference Corpus --9. Resolution approaches --10. Mention detection --11. Rule-based approach --12. Statistical approach --13. Manual annotation evaluation --14. Evaluation approaches --15. Evaluation results --16. Conclusions --17. Perspectives --Acknowledgements --Bibliography‘Coreference’ presents specificities of reference, anaphora and coreference in Polish, establish identity-of-reference annotation model and present methodology used to create the corpus of Polish general nominal coreference. Various resolution approaches are presented, followed by their evaluation. By discussing the subsequent steps of building a coreference-related component of the natural language processing toolset and offering deeper explanation of the decisions taken, this volume might also serve as a reference book on state-of the art methods of carrying out coreference projects for new languages and a tutorial for NLP practitioners. Apart from serving as a description of the fi rst complete approach to annotation and resolution of direct nominal coreference for Polish, this book is a useful starting point for further work on other types of anaphora/coreference, semantic annotation, cognitive linguistics (related to the topic of near-identity, discussed in the book) etc. With extended tutorial-like sections on important subtopics, such as evaluation metrics for coreference resolution, it can prove useful to both researchers and practitioners interested in semantic description of Balto-Slavic languages and their processing, engineers developing language resources, tools and linguistic processing chains, as well as computational linguists in general.Polish languageSemanticsPolish languageSyntaxReference (Linguistics)Anaphora (Linguistics)Applied Linguistics.Corpus Linguistics.Discourse Analysis.Natural Language Processing.Speech Processing.Speech Technoloy.Text Analysis.Polish languageSemantics.Polish languageSyntax.Reference (Linguistics)Anaphora (Linguistics)491.8/501456Ogrodniczuk Maciej , authttp://id.loc.gov/vocabulary/relators/aut1696424Ogrodniczuk MaciejMiAaPQMiAaPQMiAaPQBOOK9910827012303321Coreference4076395UNINA