File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: A dependency parser for tweets

TitleA dependency parser for tweets
Authors
Kong, LingpengSchneider, NathanSwayamdipta, SwabhaBhatia, ArchnaDyer, ChrisSmith, Noah A.
Issue Date2014
Citation
2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25-29 October 2014. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, p. 1001-1012 How to Cite?
DOI: http://dx.doi.org/10.3115/v1/d14-1108
Abstract© 2014 Association for Computational Linguistics. We describe a new dependency parser for English tweets, TWEEBOPARSER. The parser builds on several contributions: new syntactic annotations for a corpus of tweets (TWEEBANK), with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new approach to exploiting out-of-domain Penn Treebank data. Our experiments show that the parser achieves over 80% unlabeled attachment accuracy on our new, high-quality test set and measure the benefit of our contributions.
Persistent Identifierhttp://hdl.handle.net/10722/296123

 

DC FieldValueLanguage
dc.contributor.authorKong, Lingpeng-
dc.contributor.authorSchneider, Nathan-
dc.contributor.authorSwayamdipta, Swabha-
dc.contributor.authorBhatia, Archna-
dc.contributor.authorDyer, Chris-
dc.contributor.authorSmith, Noah A.-
dc.date.accessioned2021-02-11T04:52:53Z-
dc.date.available2021-02-11T04:52:53Z-
dc.date.issued2014-
dc.identifier.citation2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25-29 October 2014. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, p. 1001-1012-
dc.identifier.urihttp://hdl.handle.net/10722/296123-
dc.description.abstract© 2014 Association for Computational Linguistics. We describe a new dependency parser for English tweets, TWEEBOPARSER. The parser builds on several contributions: new syntactic annotations for a corpus of tweets (TWEEBANK), with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new approach to exploiting out-of-domain Penn Treebank data. Our experiments show that the parser achieves over 80% unlabeled attachment accuracy on our new, high-quality test set and measure the benefit of our contributions.-
dc.languageeng-
dc.relation.ispartofProceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleA dependency parser for tweets-
dc.typeConference_Paper-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.3115/v1/d14-1108-
dc.identifier.scopuseid_2-s2.0-84961307861-
dc.identifier.spage1001-
dc.identifier.epage1012-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats