Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

Linzi Xing, Wen Xiao, Giuseppe Carenini


Abstract
In news articles the lead bias is a common phenomenon that usually dominates the learning signals for neural extractive summarizers, severely limiting their performance on data with different or even no bias. In this paper, we introduce a novel technique to demote lead bias and make the summarizer focus more on the content semantics. Experiments on two news corpora with different degrees of lead bias show that our method can effectively demote the model’s learned lead bias and improve its generality on out-of-distribution data, with little to no performance loss on in-distribution data.
Anthology ID:
2021.acl-short.119
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
948–954
Language:
URL:
https://aclanthology.org/2021.acl-short.119
DOI:
10.18653/v1/2021.acl-short.119
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.119.pdf