Lite Unified Modeling for Discriminative Reading Comprehension

Yilin Zhao, Hai Zhao, Libin Shen, Yinggong Zhao


Abstract
As a broad and major category in machine reading comprehension (MRC), the generalized goal of discriminative MRC is answer prediction from the given materials. However, the focuses of various discriminative MRC tasks may be diverse enough: multi-choice MRC requires model to highlight and integrate all potential critical evidence globally; while extractive MRC focuses on higher local boundary preciseness for answer extraction. Among previous works, there lacks a unified design with pertinence for the overall discriminative MRC tasks. To fill in above gap, we propose a lightweight POS-Enhanced Iterative Co-Attention Network (POI-Net) as the first attempt of unified modeling with pertinence, to handle diverse discriminative MRC tasks synchronously. Nearly without introducing more parameters, our lite unified design brings model significant improvement with both encoder and decoder components. The evaluation results on four discriminative MRC benchmarks consistently indicate the general effectiveness and applicability of our model, and the code is available at https://github.com/Yilin1111/poi-net.
Anthology ID:
2022.acl-long.594
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8682–8695
Language:
URL:
https://aclanthology.org/2022.acl-long.594
DOI:
10.18653/v1/2022.acl-long.594
Bibkey:
Cite (ACL):
Yilin Zhao, Hai Zhao, Libin Shen, and Yinggong Zhao. 2022. Lite Unified Modeling for Discriminative Reading Comprehension. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8682–8695, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Lite Unified Modeling for Discriminative Reading Comprehension (Zhao et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.594.pdf
Software:
 2022.acl-long.594.software.zip
Code
 yilin1111/poi-net
Data
DREAMRACESQuAD