Skip to main navigation Skip to search Skip to main content

Negation scope detection with recurrent neural networks models in review texts

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Identifying negation scopes in a text is an important subtask of information extraction, that can benefit other natural language processing tasks, like relation extraction, question answering and sentiment analysis. And serves the task of social media text understanding. The task of negation scope detection can be regarded as a token-level sequence labeling problem. In this paper, we propose different models based on recurrent neural networks (RNNs) and word embedding that can be successfully applied to such tasks without any task-specific feature engineering efforts. Our experimental results show that RNNs, without using any hand-crafted features, outperform feature-rich CRF-based model.

Original languageEnglish
Title of host publicationSocial Computing - 2nd International Conference of Young Computer Scientists, Engineers and Educators, ICYCSEE 2016, Proceedings
EditorsWanxiang Che, Hongzhi Wang, Shaoliang Peng, Weipeng Jing, Guanglu Sun, Xianhua Song, Zeguang Lu, Qilong Han, Junyu Lin, Hongtao Song
PublisherSpringer Verlag
Pages494-508
Number of pages15
ISBN (Print)9789811020520
DOIs
StatePublished - 2016
Event2nd International Conference on Young Computer Scientists, Engineers and Educators, ICYCSEE 2016 - Harbin, China
Duration: 20 Aug 201622 Aug 2016

Publication series

NameCommunications in Computer and Information Science
Volume623
ISSN (Print)1865-0929

Conference

Conference2nd International Conference on Young Computer Scientists, Engineers and Educators, ICYCSEE 2016
Country/TerritoryChina
CityHarbin
Period20/08/1622/08/16

Keywords

  • Natural language processing
  • Negation scope detection
  • Recurrent neural networks

Fingerprint

Dive into the research topics of 'Negation scope detection with recurrent neural networks models in review texts'. Together they form a unique fingerprint.

Cite this