Character-level feature extraction with densely connected networks

Chanhee Lee, Young Bum Kim, Dongyub Lee, Heui Seok Lim

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

3 Citations (Scopus)

Abstract

Generating character-level features is an important step for achieving good results in various natural language processing tasks. To alleviate the need for human labor in generating hand-crafted features, methods that utilize neural architectures such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) to automatically extract such features have been proposed and have shown great results. However, CNN generates position-independent features, and RNN is slow since it needs to process the characters sequentially. In this paper, we propose a novel method of using a densely connected network to automatically extract character-level features. The proposed method does not require any language or task specific assumptions, and shows robustness and effectiveness while being faster than CNN- or RNN-based methods. Evaluating this method on three sequence labeling tasks - slot tagging, Part-of-Speech (POS) tagging, and Named-Entity Recognition (NER) - we obtain state-of-the-art performance with a 96.62 F1-score and 97.73% accuracy on slot tagging and POS tagging, respectively, and comparable performance to the state-of-the-art 91.13 F1-score on NER.

Original languageEnglish
Title of host publicationCOLING 2018 - 27th International Conference on Computational Linguistics, Proceedings
EditorsEmily M. Bender, Leon Derczynski, Pierre Isabelle
PublisherAssociation for Computational Linguistics (ACL)
Pages3228-3239
Number of pages12
ISBN (Electronic)9781948087506
Publication statusPublished - 2018
Event27th International Conference on Computational Linguistics, COLING 2018 - Santa Fe, United States
Duration: 2018 Aug 202018 Aug 26

Publication series

NameCOLING 2018 - 27th International Conference on Computational Linguistics, Proceedings

Conference

Conference27th International Conference on Computational Linguistics, COLING 2018
Country/TerritoryUnited States
CitySanta Fe
Period18/8/2018/8/26

Bibliographical note

Funding Information:
This research was supported by the MSIT (Ministry of Science and ICT), South Korea, under the ITRC (Information Technology Research Center) support program (”Research and Development of Human-Inspired Multiple Intelligence”) supervised by the IITP (Institute for Information & Communications Technology Promotion). Additionally, this work was supported by the National Research Foundation of Korea (NRF) grant funded by the South Korean government (MSIP) (No. NRF-2016R1A2B2015912).

Publisher Copyright:
© 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Character-level feature extraction with densely connected networks'. Together they form a unique fingerprint.

Cite this