@inproceedings{ding-etal-2023-unified,
title = "A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific {NLP} Tasks",
author = "Ding, Ruiqing and
Han, Xiao and
Wang, Leye",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.24",
doi = "10.18653/v1/2023.findings-acl.24",
pages = "353--369",
abstract = "By focusing the pre-training process on domain-specific corpora, some domain-specific pre-trained language models (PLMs) have achieved state-of-the-art results. However, it is under-investigated to design a unified paradigm to inject domain knowledge in the PLM fine-tuning stage. We propose KnowledgeDA, a unified domain language model development service to enhance the task-specific training procedure with domain knowledge graphs. Given domain-specific task texts input, KnowledgeDA can automatically generate a domain-specific language model following three steps: (i) localize domain knowledge entities in texts via an embedding-similarity approach; (ii) generate augmented samples by retrieving replaceable domain entity pairs from two views of both knowledge graph and training data; (iii) select high-quality augmented samples for fine-tuning via confidence-based assessment. We implement a prototype of KnowledgeDA to learn language models for two domains, healthcare and software development. Experiments on domain-specific text classification and QA tasks verify the effectiveness and generalizability of KnowledgeDA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2023-unified">
<titleInfo>
<title>A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruiqing</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leye</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<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">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>By focusing the pre-training process on domain-specific corpora, some domain-specific pre-trained language models (PLMs) have achieved state-of-the-art results. However, it is under-investigated to design a unified paradigm to inject domain knowledge in the PLM fine-tuning stage. We propose KnowledgeDA, a unified domain language model development service to enhance the task-specific training procedure with domain knowledge graphs. Given domain-specific task texts input, KnowledgeDA can automatically generate a domain-specific language model following three steps: (i) localize domain knowledge entities in texts via an embedding-similarity approach; (ii) generate augmented samples by retrieving replaceable domain entity pairs from two views of both knowledge graph and training data; (iii) select high-quality augmented samples for fine-tuning via confidence-based assessment. We implement a prototype of KnowledgeDA to learn language models for two domains, healthcare and software development. Experiments on domain-specific text classification and QA tasks verify the effectiveness and generalizability of KnowledgeDA.</abstract>
<identifier type="citekey">ding-etal-2023-unified</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.24</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.24</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>353</start>
<end>369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP Tasks
%A Ding, Ruiqing
%A Han, Xiao
%A Wang, Leye
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ding-etal-2023-unified
%X By focusing the pre-training process on domain-specific corpora, some domain-specific pre-trained language models (PLMs) have achieved state-of-the-art results. However, it is under-investigated to design a unified paradigm to inject domain knowledge in the PLM fine-tuning stage. We propose KnowledgeDA, a unified domain language model development service to enhance the task-specific training procedure with domain knowledge graphs. Given domain-specific task texts input, KnowledgeDA can automatically generate a domain-specific language model following three steps: (i) localize domain knowledge entities in texts via an embedding-similarity approach; (ii) generate augmented samples by retrieving replaceable domain entity pairs from two views of both knowledge graph and training data; (iii) select high-quality augmented samples for fine-tuning via confidence-based assessment. We implement a prototype of KnowledgeDA to learn language models for two domains, healthcare and software development. Experiments on domain-specific text classification and QA tasks verify the effectiveness and generalizability of KnowledgeDA.
%R 10.18653/v1/2023.findings-acl.24
%U https://aclanthology.org/2023.findings-acl.24
%U https://doi.org/10.18653/v1/2023.findings-acl.24
%P 353-369
Markdown (Informal)
[A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP Tasks](https://aclanthology.org/2023.findings-acl.24) (Ding et al., Findings 2023)
ACL