[go: up one dir, main page]

Retrieval-Augmented Domain Adaptation of Language Models

Benfeng Xu, Chunxu Zhao, Wenbin Jiang, PengFei Zhu, Songtai Dai, Chao Pang, Zhuo Sun, Shuohuan Wang, Yu Sun


Abstract
Language models pretrained on general domain corpora usually exhibit considerable degradation when generalizing to downstream tasks of specialized domains. Existing approaches try to construct PLMs for each specific domains either from scratch or through further pretraining, which not only costs substantial resources, but also fails to cover all target domains at various granularity. In this work, we propose RADA, a novel Retrieval-Augmented framework for Domain Adaptation. We first construct a textual corpora that covers the downstream task at flexible domain granularity and resource availability. We employ it as a pluggable datastore to retrieve informative background knowledge, and integrate them into the standard language model framework to augment representations. We then propose a two-level selection scheme to integrate the most relevant information while alleviating irrelevant noises. Specifically, we introduce a differentiable sampling module as well as an attention mechanism to achieve both passage-level and word-level selection. Such a retrieval-augmented framework enables domain adaptation of language models with flexible domain coverage and fine-grained domain knowledge integration. We conduct comprehensive experiments across biomedical, science and legal domains to demonstrate the effectiveness of the overall framework, and its advantage over existing solutions.
Anthology ID:
2023.repl4nlp-1.5
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:
54–64
Language:
URL:
https://aclanthology.org/2023.repl4nlp-1.5
DOI:
10.18653/v1/2023.repl4nlp-1.5
Bibkey:
Cite (ACL):
Benfeng Xu, Chunxu Zhao, Wenbin Jiang, PengFei Zhu, Songtai Dai, Chao Pang, Zhuo Sun, Shuohuan Wang, and Yu Sun. 2023. Retrieval-Augmented Domain Adaptation of Language Models. In Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023), pages 54–64, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Retrieval-Augmented Domain Adaptation of Language Models (Xu et al., RepL4NLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.repl4nlp-1.5.pdf
Video:
 https://aclanthology.org/2023.repl4nlp-1.5.mp4