Memory-Based Invariance Learning for Out-of-Domain Text Classification

Chen Jia, Yue Zhang


Abstract
We investigate the task of out-of-domain (OOD) text classification with the aim of extending a classification model, trained on multiple source domains, to an unseen target domain. Recent studies have shown that learning invariant representations can enhance the performance of OOD generalization. However, the inherent disparity in data distribution across different domains poses challenges for achieving effective invariance learning. This study addresses this issue by employing memory augmentations. Specifically, we augment the original feature space using key-value memory and employ a meta-learning-based approach to enhance the quality of the invariant representations. Experimental results on sentiment analysis and natural language inference tasks show the effectiveness of memory-based method for invariance learning, leading to state-of-the-art performance on six datasets.
Anthology ID:
2023.emnlp-main.101
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:
1635–1647
Language:
URL:
https://aclanthology.org/2023.emnlp-main.101
DOI:
10.18653/v1/2023.emnlp-main.101
Bibkey:
Cite (ACL):
Chen Jia and Yue Zhang. 2023. Memory-Based Invariance Learning for Out-of-Domain Text Classification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1635–1647, Singapore. Association for Computational Linguistics.
Cite (Informal):
Memory-Based Invariance Learning for Out-of-Domain Text Classification (Jia & Zhang, EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2023.emnlp-main.101.pdf