Title: Negation scope detection with recurrent neural networks models in review texts

Authors: Lydia Lazib; Yanyan Zhao; Bing Qin; Ting Liu

Addresses: Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin 150001, China ' Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin 150001, China ' Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin 150001, China ' Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin 150001, China

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 labelling 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 effort. Our experimental results show that RNNs, without using any hand-crafted features, outperform feature-rich CRF-based model.

Keywords: negation scope detection; natural language processing; recurrent neural networks; RNNs.

DOI: 10.1504/IJHPCN.2019.097501

International Journal of High Performance Computing and Networking, 2019 Vol.13 No.2, pp.211 - 221

Received: 26 Jun 2016
Accepted: 12 Sep 2016
Published online: 25 Jan 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article