Improving Language Models’ Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary

Myeongjun Jang, Thomas Lukasiewicz


Abstract
The non-humanlike behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon of such faulty behaviours is the generation of inconsistent predictions, which produces logically contradictory results, such as generating different predictions for texts delivering the same meaning or violating logical properties. Previous studies exploited data augmentation or implemented specialised loss functions to alleviate the issue. However, their usage is limited, because they consume expensive training resources for large-sized PLMs and can only handle a certain consistency type. To this end, we propose a practical approach that alleviates the inconsistent behaviour issue by fundamentally improving PLMs’ meaning awareness. Based on the conceptual role theory, our method allows PLMs to capture accurate meaning by learning precise interrelationships between concepts from word-definition pairs in a dictionary. Next, we propose an efficient parameter integration technique that updates only a few additional parameters to combine the learned interrelationship with PLMs’ pre-trained knowledge. Our experimental results reveal that the approach can concurrently improve multiple types of consistency, enables efficient knowledge integration, and easily applies to other languages.
Anthology ID:
2023.emnlp-main.527
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8496–8510
Language:
URL:
https://aclanthology.org/2023.emnlp-main.527
DOI:
10.18653/v1/2023.emnlp-main.527
Bibkey:
Cite (ACL):
Myeongjun Jang and Thomas Lukasiewicz. 2023. Improving Language Models’ Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8496–8510, Singapore. Association for Computational Linguistics.
Cite (Informal):
Improving Language Models’ Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary (Jang & Lukasiewicz, EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.527.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.527.mp4