Winnowing Knowledge for Multi-choice Question Answering

Page view(s)
18
Checked on May 10, 2022
Winnowing Knowledge for Multi-choice Question Answering
Title:
Winnowing Knowledge for Multi-choice Question Answering
Other Titles:
The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)
DOI:
Keywords:
Publication Date:
07 November 2021
Citation:
Li, Y., Zou, B., Li, Z., Aw, AT., Hong, Y., Zhu., Q. Winnowing Knowledge for Multi-choice Question Answering. The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021). 2021
Abstract:
We tackle multi-choice question answering. Acquiring related commonsense knowledge to the question and options facilitates the recognition of the correct answer. However, the current reasoning models suffer from the noises in the retrieved knowledge. In this paper, we propose a novel encoding method which is able to conduct interception and soft filtering. This contributes to the harvesting and absorption of representative information with less interference from noises. We experiment on CommonsenseQA. Experimental results illustrate that our method yields substantial and consistent improvements compared to the strong Bert, RoBERTa and Albert-based baselines.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This work is supported by the national Natural Science Foundation of China (NSFC) and Major National Science and Technology project of China, via Grant Nos.62076174, 61836007, 2020YBF1313601.
Description:
ISBN:
NA
Files uploaded:

Files uploaded:

File Size Format Action
2021findings-emnlp100.pdf 355.02 KB PDF Open