ML Anthology

SWIM: A Simple Word Interaction Model for Implicit Discourse Relation Recognition

Wenqiang Lei, Xuancong Wang, Meichun Liu, Ilija Ilievski, Xiangnan He, Min-Yen Kan
IJCAI 2017 pp. 4026-4032
doi:10.24963/IJCAI.2017/562 /ijcai/2017/lei2017ijcai-swim/

Abstract

Capturing the semantic interaction of pairs of words across arguments and proper argument representation are both crucial issues in implicit discourse relation recognition. The current state-of-the-art represents arguments as distributional vectors that are computed via bi-directional Long Short-Term Memory networks (BiLSTMs), known to have significant model complexity. In contrast, we demonstrate that word-weighted averaging can encode argument representation which can incorporate word pair information efficiently. By saving an order of magnitude in parameters, our proposed model achieves equivalent performance, but trains seven times faster.

PDF IJCAI Semantic Scholar

Cite

Text

Lei et al. "SWIM: A Simple Word Interaction Model for Implicit Discourse Relation Recognition." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/562

Markdown

[Lei et al. "SWIM: A Simple Word Interaction Model for Implicit Discourse Relation Recognition." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/lei2017ijcai-swim/) doi:10.24963/IJCAI.2017/562

BibTeX

@inproceedings{lei2017ijcai-swim,
  title     = {{SWIM: A Simple Word Interaction Model for Implicit Discourse Relation Recognition}},
  author    = {Lei, Wenqiang and Wang, Xuancong and Liu, Meichun and Ilievski, Ilija and He, Xiangnan and Kan, Min-Yen},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {4026-4032},
  doi       = {10.24963/IJCAI.2017/562},
  url       = {https://mlanthology.org/ijcai/2017/lei2017ijcai-swim/}
}