@inproceedings{xu-etal-2023-retrieval,
title = "Retrieval-Augmented Domain Adaptation of Language Models",
author = "Xu, Benfeng and
Zhao, Chunxu and
Jiang, Wenbin and
Zhu, PengFei and
Dai, Songtai and
Pang, Chao and
Sun, Zhuo and
Wang, Shuohuan and
Sun, Yu",
editor = "Can, Burcu and
Mozes, Maximilian and
Cahyawijaya, Samuel and
Saphra, Naomi and
Kassner, Nora and
Ravfogel, Shauli and
Ravichander, Abhilasha and
Zhao, Chen and
Augenstein, Isabelle and
Rogers, Anna and
Cho, Kyunghyun and
Grefenstette, Edward and
Voita, Lena",
booktitle = "Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.repl4nlp-1.5",
doi = "10.18653/v1/2023.repl4nlp-1.5",
pages = "54--64",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2023-retrieval">
<titleInfo>
<title>Retrieval-Augmented Domain Adaptation of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benfeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunxu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">PengFei</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songtai</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuohuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Mozes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shauli</namePart>
<namePart type="family">Ravfogel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhilasha</namePart>
<namePart type="family">Ravichander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Voita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">xu-etal-2023-retrieval</identifier>
<identifier type="doi">10.18653/v1/2023.repl4nlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.repl4nlp-1.5</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>54</start>
<end>64</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval-Augmented Domain Adaptation of Language Models
%A Xu, Benfeng
%A Zhao, Chunxu
%A Jiang, Wenbin
%A Zhu, PengFei
%A Dai, Songtai
%A Pang, Chao
%A Sun, Zhuo
%A Wang, Shuohuan
%A Sun, Yu
%Y Can, Burcu
%Y Mozes, Maximilian
%Y Cahyawijaya, Samuel
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Ravfogel, Shauli
%Y Ravichander, Abhilasha
%Y Zhao, Chen
%Y Augenstein, Isabelle
%Y Rogers, Anna
%Y Cho, Kyunghyun
%Y Grefenstette, Edward
%Y Voita, Lena
%S Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F xu-etal-2023-retrieval
%X 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.
%R 10.18653/v1/2023.repl4nlp-1.5
%U https://aclanthology.org/2023.repl4nlp-1.5
%U https://doi.org/10.18653/v1/2023.repl4nlp-1.5
%P 54-64
Markdown (Informal)
[Retrieval-Augmented Domain Adaptation of Language Models](https://aclanthology.org/2023.repl4nlp-1.5) (Xu et al., RepL4NLP 2023)
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.