4.6 Article

Boosting implicit discourse relation recognition with connective-based word embeddings

Journal

NEUROCOMPUTING
Volume 369, Issue -, Pages 39-49

Publisher

ELSEVIER
DOI: 10.1016/j.neucom.2019.08.081

Keywords

Connective-based word embeddings; Implicit discourse relation recognition; Connective classification; Neural network

Funding

  1. Natural Science Foundation of China [61866012]
  2. Natural Science Foundation of Jiangxi Province [20181BAB202012]
  3. Science and Technology Research Project of Education Department of Jiangxi Province [GJJ180329]

Ask authors/readers for more resources

Implicit discourse relation recognition is the performance bottleneck of discourse structure analysis. To alleviate the shortage of training data, previous methods usually use explicit discourse data, which are naturally labeled by connectives, as additional training data. However, it is often difficult for them to integrate large amounts of explicit discourse data because of the noise problem. In this paper, we propose a simple and effective method to leverage massive explicit discourse data. Specifically, we learn connective-based word embeddings (CBWE) by performing connective classification on explicit discourse data. The learned CBWE is capable of capturing discourse relationships between words, and can be used as pre-trained word embeddings for implicit discourse relation recognition. On both the English PDTB and Chinese CDTB data sets, using CBWE achieves significant improvements over baselines with general word embeddings, and better performance than baselines integrating explicit discourse data. By combining CBWE with a strong baseline, we achieve the state-of-the-art performance. (C) 2019 Elsevier B.V. All rights reserved.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available