DAGN: Discourse-Aware Graph Network for Logical Reasoning
Yinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang
Abstract
Recent QA with logical reasoning questions requires passage-level relations among the sentences. However, current approaches still focus on sentence-level relations interacting among tokens. In this work, we explore aggregating passage-level clues for solving logical reasoning QA by using discourse-based information. We propose a discourse-aware graph network (DAGN) that reasons relying on the discourse structure of the texts. The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks. Experiments are conducted on two logical reasoning QA datasets, ReClor and LogiQA, and our proposed DAGN achieves competitive results. The source code is available at https://github.com/Eleanor-H/DAGN.
BibTeX
@inproceedings{huang-etal-2021-dagn,
title = "{DAGN}: Discourse-Aware Graph Network for Logical Reasoning",
author = "Huang, Yinya and
Fang, Meng and
Cao, Yu and
Wang, Liwei and
Liang, Xiaodan",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.467/",
doi = "10.18653/v1/2021.naacl-main.467",
pages = "5848--5855"
}