Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Peifeng Wang, Nanyun Peng, Filip Ilievski, Pedro Szekely, Xiang Ren

Abstract
Commonsense question answering (QA) requires background knowledge which is not explicitly stated in a given context. Prior works use commonsense knowledge graphs (KGs) to obtain this knowledge for reasoning. However, relying entirely on these KGs may not suffice, considering their limited coverage and the contextual dependence of their knowledge. In this paper, we augment a general commonsense QA framework with a knowledgeable path generator. By extrapolating over existing paths in a KG with a state-of-the-art language model, our generator learns to connect a pair of entities in text with a dynamic, and potentially novel, multi-hop relational path. Such paths can provide structured evidence for solving commonsense questions without fine-tuning the path generator. Experiments on two datasets show the superiority of our method over previous works which fully rely on knowledge from KGs (with up to 6% improvement in accuracy), across various amounts of training data. Further evaluation suggests that the generated paths are typically interpretable, novel, and relevant to the task.
Anthology ID:
2020.findings-emnlp.369
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4129–4140
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.369
DOI:
10.18653/v1/2020.findings-emnlp.369
Bibkey:
Cite (ACL):
Peifeng Wang, Nanyun Peng, Filip Ilievski, Pedro Szekely, and Xiang Ren. 2020. Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4129–4140, Online. Association for Computational Linguistics.
Cite (Informal):
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering (Wang et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2020.findings-emnlp.369.pdf
Code
 wangpf3/Commonsense-Path-Generator
Data
CommonsenseQA, ConceptNet, OpenBookQA
PDF Search Code