Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks

Siddharth Varia, Christopher Hidey, Tuhin Chakrabarty


Abstract
Word pairs across argument spans have been shown to be effective for predicting the discourse relation between them. We propose an approach to distill knowledge from word pairs for discourse relation classification with convolutional neural networks by incorporating joint learning of implicit and explicit relations. Our novel approach of representing the input as word pairs achieves state-of-the-art results on four-way classification of both implicit and explicit relations as well as one of the binary classification tasks. For explicit relation prediction, we achieve around 20% error reduction on the four-way task. At the same time, compared to a two-layered Bi-LSTM-CRF model, our model is able to achieve these results with half the number of learnable parameters and approximately half the amount of training time.
Anthology ID:
W19-5951
Volume:
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
Month:
September
Year:
2019
Address:
Stockholm, Sweden
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
442–452
Language:
URL:
https://aclanthology.org/W19-5951
DOI:
10.18653/v1/W19-5951
Bibkey:
Cite (ACL):
Siddharth Varia, Christopher Hidey, and Tuhin Chakrabarty. 2019. Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 442–452, Stockholm, Sweden. Association for Computational Linguistics.
Cite (Informal):
Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks (Varia et al., SIGDIAL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5951.pdf