Learning connective-based word representations for implicit discourse relation identification
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
We introduce a simple semi-supervised ap-proach to improve implicit discourse relation identification. This approach harnesses large amounts of automatically extracted discourse connectives along with their arguments to con-struct new distributional word representations. Specifically, we represent words in the space of discourse connectives as a way to directly encode their rhetorical function. Experiments on the Penn Discourse Treebank demonstrate the effectiveness of these task-tailored repre-sentations in predicting implicit discourse re-lations. Our results indeed show that, despite their simplicity, these connective-based rep-resentations outperform various off-the-shelf word embeddings, and achieve state-of-the-art performance on this problem.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP-16) |
Number of pages | 11 |
Publisher | Association for Computational Linguistics |
Publication date | 2016 |
Pages | 203-213 |
ISBN (Electronic) | 978-1-945626-25-8 |
Publication status | Published - 2016 |
Event | 2016 Conference on Empirical Methods in Natural Language Processing - Austin, United States Duration: 1 Nov 2016 → 5 Nov 2016 |
Conference
Conference | 2016 Conference on Empirical Methods in Natural Language Processing |
---|---|
Land | United States |
By | Austin |
Periode | 01/11/2016 → 05/11/2016 |
Links
- http://aclweb.org/anthology/D/D16/D16-1020.pdf
Final published version
ID: 178453451