Publication:
CharNER: character-level named entity recognition

Placeholder

School / College / Institute

Organizational Unit

Program

KU Authors

Co-Authors

N/A

Publication Date

Language

Embargo Status

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

We describe and evaluate a character-level tagger for language-independent Named Entity Recognition (NER). Instead of words, a sentence is represented as a sequence of characters. The model consists of stacked bidirectional LSTMs which inputs characters and outputs tag probabilities for each character. These probabilities are then converted to consistent word level named entity tags using a Viterbi decoder. We are able to achieve close to state-of-the-art NER performance in seven languages with the same basic model using only labeled NER data and no hand-engineered features or other external resources like syntactic taggers or Gazetteers. 

Source

Publisher

Association for Computational Linguistics (ACL)

Subject

Computer engineering

Citation

Has Part

Source

COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: Technical Papers

Book Series Title

Edition

DOI

item.page.datauri

Rights

Copyrights Note

Endorsement

Review

Supplemented By

Referenced By

0

Views

0

Downloads