Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition
Wei Xiang, Bang Wang, Lu Dai, Yijun Mo
Abstract
Prior studies use one attention mechanism to improve contextual semantic representation learning for implicit discourse relation recognition (IDRR). However, diverse relation senses may benefit from different attention mechanisms. We also argue that some linguistic relation in between two words can be further exploited for IDRR. This paper proposes a Multi-Attentive Neural Fusion (MANF) model to encode and fuse both semantic connection and linguistic evidence for IDRR. In MANF, we design a Dual Attention Network (DAN) to learn and fuse two kinds of attentive representation for arguments as its semantic connection. We also propose an Offset Matrix Network (OMN) to encode the linguistic relations of word-pairs as linguistic evidence. Our MANF model achieves the state-of-the-art results on the PDTB 3.0 corpus.
BibTeX
@inproceedings{xiang-etal-2022-encoding,
title = "Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition",
author = "Xiang, Wei and
Wang, Bang and
Dai, Lu and
Mo, Yijun",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.256/",
doi = "10.18653/v1/2022.findings-acl.256",
pages = "3247--3257"
}