Deep Affix Features Improve Neural Named Entity Recognizers

Vikas Yadav, Rebecca Sharp, Steven Bethard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

35 Scopus citations

Abstract

We propose a practical model for named entity recognition (NER) that combines word and character-level information with a specific learned representation of the prefixes and suffixes of the word. We apply this approach to multilingual and multi-domain NER and show that it achieves state of the art results on the CoNLL 2002 Spanish and Dutch and CoNLL 2003 German NER datasets, consistently achieving 1.5-2.3 percent over the state of the art without relying on any dictionary features. Additionally, we show improvement on SemEval 2013 task 9.1 DrugNER, achieving state of the art results on the MedLine dataset and the second best results overall (-1.3% from state of the art). We also establish a new benchmark on the I2B2 2010 Clinical NER dataset with 84.70 F-score.

Original languageEnglish (US)
Title of host publicationNAACL HLT 2018 - Lexical and Computational Semantics, SEM 2018, Proceedings of the 7th Conference
EditorsMalvina Nissim, Jonathan Berant, Alessandro Lenci
PublisherAssociation for Computational Linguistics (ACL)
Pages167-172
Number of pages6
ISBN (Electronic)9781948087223
StatePublished - 2018
Event7th Joint Conference on Lexical and Computational Semantics, SEM 2018, co-located with NAACL HLT 2018 - New Orleans, United States
Duration: Jun 5 2018Jun 6 2018

Publication series

NameNAACL HLT 2018 - Lexical and Computational Semantics, SEM 2018, Proceedings of the 7th Conference

Conference

Conference7th Joint Conference on Lexical and Computational Semantics, SEM 2018, co-located with NAACL HLT 2018
Country/TerritoryUnited States
CityNew Orleans
Period6/5/186/6/18

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Deep Affix Features Improve Neural Named Entity Recognizers'. Together they form a unique fingerprint.

Cite this