Enhancing text comprehension for Question Answering with Contrastive Learning

Seungyeon Lee, Minho Lee


Abstract
Although Question Answering (QA) have advanced to the human-level language skills in NLP tasks, there is still a problem: the QA model gets confused when there are similar sentences or paragraphs. Existing studies focus on enhancing the text understanding of the candidate answers to improve the overall performance of the QA models. However, since these methods focus on re-ranking queries or candidate answers, they fail to resolve the confusion when many generated answers are similar to the expected answer. To address these issues, we propose a novel contrastive learning framework called ContrastiveQA that alleviates the confusion problem in answer extraction. We propose a supervised method where we generate positive and negative samples from the candidate answers and the given answer, respectively. We thus introduce ContrastiveQA, which uses contrastive learning with sampling data to reduce incorrect answers. Experimental results on four QA benchmarks show the effectiveness of the proposed method.
Anthology ID:
2023.repl4nlp-1.7
Volume:
Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Burcu Can, Maximilian Mozes, Samuel Cahyawijaya, Naomi Saphra, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Chen Zhao, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Lena Voita
Venue:
RepL4NLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
75–86
Language:
URL:
https://aclanthology.org/2023.repl4nlp-1.7
DOI:
10.18653/v1/2023.repl4nlp-1.7
Bibkey:
Cite (ACL):
Seungyeon Lee and Minho Lee. 2023. Enhancing text comprehension for Question Answering with Contrastive Learning. In Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023), pages 75–86, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Enhancing text comprehension for Question Answering with Contrastive Learning (Lee & Lee, RepL4NLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.repl4nlp-1.7.pdf