Example-based Hypernetworks for Multi-source Adaptation to Unseen Domains

Tomer Volk, Eyal Ben-David, Ohad Amosy, Gal Chechik, Roi Reichart


Abstract
As Natural Language Processing (NLP) algorithms continually achieve new milestones, out-of-distribution generalization remains a significant challenge. This paper addresses the issue of multi-source adaptation for unfamiliar domains: We leverage labeled data from multiple source domains to generalize to unknown target domains at training. Our innovative framework employs example-based Hypernetwork adaptation: a T5 encoder-decoder initially generates a unique signature from an input example, embedding it within the source domains’ semantic space. This signature is subsequently utilized by a Hypernetwork to generate the task classifier’s weights. In an advanced version, the signature also enriches the input example’s representation. We evaluated our method across two tasks—sentiment classification and natural language inference—in 29 adaptation scenarios, where it outpaced established algorithms. We also compare our finetuned architecture to few-shot GPT-3, demonstrating its effectiveness in essential use cases. To the best of our knowledge, this marks the first application of Hypernetworks to the adaptation for unknown domains.
Anthology ID:
2023.findings-emnlp.610
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9096–9113
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.610
DOI:
10.18653/v1/2023.findings-emnlp.610
Bibkey:
Cite (ACL):
Tomer Volk, Eyal Ben-David, Ohad Amosy, Gal Chechik, and Roi Reichart. 2023. Example-based Hypernetworks for Multi-source Adaptation to Unseen Domains. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9096–9113, Singapore. Association for Computational Linguistics.
Cite (Informal):
Example-based Hypernetworks for Multi-source Adaptation to Unseen Domains (Volk et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.610.pdf