CoLISA: Inner Interaction via Contrastive Learning for Multi-choice Reading Comprehension

Page view(s)
20
Checked on Jan 30, 2025
CoLISA: Inner Interaction via Contrastive Learning for Multi-choice Reading Comprehension
Title:
CoLISA: Inner Interaction via Contrastive Learning for Multi-choice Reading Comprehension
Journal Title:
Lecture Notes in Computer Science - ECIR 2023
Keywords:
Publication Date:
16 March 2023
Citation:
Dong, M., Zou, B., Li, Y., & Hong, Y. (2023). CoLISA: Inner Interaction via Contrastive Learning for Multi-choice Reading Comprehension. In Advances in Information Retrieval (pp. 264–278). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-28244-7_17
Abstract:
Multi-choice reading comprehension (MC-RC) is supposed to select the most appropriate answer from multiple candidate options by reading and comprehending a given passage and a question. Recent studies dedicate to catching the relationships within the triplet of passage, question, and option. Nevertheless, one limitation in current approaches relates to the fact that confusing distractors are often mistakenly judged as correct, due to the fact that models do not emphasize the differences between the answer alternatives. Motivated by the way humans deal with multi-choice questions by comparing given options, we propose CoLISA (Contrastive Learning and In-Sample Attention), a novel model to prudently exclude the confusing distractors. In particular, CoLISA acquires option-aware representations via contrastive learning on multiple options. Besides, in-sample attention mechanisms are applied across multiple options so that they can interact with each other. The experimental results on QuALITY and RACE demonstrate that our proposed CoLISA pays more attention to the relation between correct and distractive options, and recognizes the discrepancy between them. Meanwhile, CoLISA also reaches the state-of-the-art performance on QuALITY.
License type:
Publisher Copyright
Funding Info:
The research is supported by National Key R&D Program of China (2020YFB1313601) and National Science Foundation of China (62076174, 62076175).
Description:
This version of the article has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/978-3-031-28244-7_17
ISSN:
9783031282447
ISBN:
9783031282430
Files uploaded:

File Size Format Action
2023-ecir-dmx-colisa.pdf 490.78 KB PDF Open