TY - GEN

T1 - Learning connective-based word representations for implicit discourse relation identification

AU - Braud, Chloé Elodie

AU - Denis, Pascal

PY - 2016

Y1 - 2016

N2 - 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.

AB - 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.

M3 - Article in proceedings

SP - 203

EP - 213

BT - Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP-16)

PB - Association for Computational Linguistics

T2 - 2016 Conference on Empirical Methods in Natural Language Processing

Y2 - 1 November 2016 through 5 November 2016

ER -