Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension

Liang Wang, Sujian Li, Wei Zhao, Kewei Shen, Meng Sun, Ruoyu Jia, Jingming Liu


Abstract
Cloze-style reading comprehension has been a popular task for measuring the progress of natural language understanding in recent years. In this paper, we design a novel multi-perspective framework, which can be seen as the joint training of heterogeneous experts and aggregate context information from different perspectives. Each perspective is modeled by a simple aggregation module. The outputs of multiple aggregation modules are fed into a one-timestep pointer network to get the final answer. At the same time, to tackle the problem of insufficient labeled data, we propose an efficient sampling mechanism to automatically generate more training examples by matching the distribution of candidates between labeled and unlabeled data. We conduct our experiments on a recently released cloze-test dataset CLOTH (Xie et al., 2017), which consists of nearly 100k questions designed by professional teachers. Results show that our method achieves new state-of-the-art performance over previous strong baselines.
Anthology ID:
C18-1073
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
857–867
Language:
URL:
https://aclanthology.org/C18-1073
DOI:
Bibkey:
Cite (ACL):
Liang Wang, Sujian Li, Wei Zhao, Kewei Shen, Meng Sun, Ruoyu Jia, and Jingming Liu. 2018. Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension. In Proceedings of the 27th International Conference on Computational Linguistics, pages 857–867, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension (Wang et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/C18-1073.pdf
Data
CBTRACE