Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

Qianglong Chen, Feng Ji, Haiqing Chen, Yin Zhang


Abstract
In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research academia and industry. In this paper, we propose a novel question-answering method by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and the Cambridge Dictionary, to boost the performance. More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources. Afterward, we use a pre-trained language model to encode the question, retrieved knowledge and choices, and propose an answer choice-aware attention mechanism to fuse all hidden representations of the previous modules. Finally, the linear classifier for specific tasks is used to predict the answer. Experimental results on the CommonsenseQA dataset show that our method significantly outperforms other competitive methods and achieves the new state-of-the-art. In addition, further ablation studies demonstrate the effectiveness of our graph-based iterative knowledge retrieval module and the answer choice-aware attention module in retrieving and synthesizing background knowledge from multiple knowledge sources.
Anthology ID:
2020.coling-main.232
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2583–2594
Language:
URL:
https://aclanthology.org/2020.coling-main.232
DOI:
10.18653/v1/2020.coling-main.232
Bibkey:
Cite (ACL):
Qianglong Chen, Feng Ji, Haiqing Chen, and Yin Zhang. 2020. Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2583–2594, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources (Chen et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.232.pdf
Data
CommonsenseQAConceptNet