Low-Resource Generation of Multi-hop Reasoning Questions

Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin


Abstract
This paper focuses on generating multi-hop reasoning questions from the raw text in a low resource circumstance. Such questions have to be syntactically valid and need to logically correlate with the answers by deducing over multiple relations on several sentences in the text. Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text. Since the labeled data is limited and insufficient for training, we propose to learn the model with the help of a large scale of unlabeled data that is much easier to obtain. Such data contains rich expressive forms of the questions with structural patterns on syntax and semantics. These patterns can be estimated by the neural hidden semi-Markov model using latent variables. With latent patterns as a prior, we can regularize the generation model and produce the optimal results. Experimental results on the HotpotQA data set demonstrate the effectiveness of our model. Moreover, we apply the generated results to the task of machine reading comprehension and achieve significant performance improvements.
Anthology ID:
2020.acl-main.601
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6729–6739
Language:
URL:
https://aclanthology.org/2020.acl-main.601
DOI:
10.18653/v1/2020.acl-main.601
Bibkey:
Cite (ACL):
Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, and Jian Yin. 2020. Low-Resource Generation of Multi-hop Reasoning Questions. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6729–6739, Online. Association for Computational Linguistics.
Cite (Informal):
Low-Resource Generation of Multi-hop Reasoning Questions (Yu et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.601.pdf
Video:
 http://slideslive.com/38928709