@inproceedings{hou-etal-2022-adapters,
title = "Adapters for Enhanced Modeling of Multilingual Knowledge and Text",
author = "Hou, Yifan and
Jiao, Wenxiang and
Liu, Meizhen and
Allen, Carl and
Tu, Zhaopeng and
Sachan, Mrinmaya",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.287",
doi = "10.18653/v1/2022.findings-emnlp.287",
pages = "3902--3917",
abstract = "Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned. Language models have recently been extended to multilingual language models (MLLMs), enabling knowledge to be learned across hundreds of languages. Meanwhile, knowledge graphs contain facts in an explicit triple format, which require careful and costly curation and are only available in a few high-resource languages, restricting their research and application. To address these issues, we propose to enhance MLLMs with knowledge from multilingual knowledge graphs (MLKGs) so as to tackle language and knowledge graph tasks across many languages, including low-resource ones. Specifically, we introducea lightweight adapter set to enhance MLLMs with cross-lingual entity alignment and facts from MLKGs for many languages. Experiments on common benchmarks show that such enhancement benefits both MLLMs and MLKGs, achieving: (1) comparable or improved performance for knowledge graph completion and entity alignment relative to baselines, especially for low-resource languages (for which knowledge graphs are unavailable); and (2) improved MLLM performance on language understanding tasks that require multilingual factual knowledge; all while maintaining performance on other general language tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hou-etal-2022-adapters">
<titleInfo>
<title>Adapters for Enhanced Modeling of Multilingual Knowledge and Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxiang</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meizhen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Allen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaopeng</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mrinmaya</namePart>
<namePart type="family">Sachan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned. Language models have recently been extended to multilingual language models (MLLMs), enabling knowledge to be learned across hundreds of languages. Meanwhile, knowledge graphs contain facts in an explicit triple format, which require careful and costly curation and are only available in a few high-resource languages, restricting their research and application. To address these issues, we propose to enhance MLLMs with knowledge from multilingual knowledge graphs (MLKGs) so as to tackle language and knowledge graph tasks across many languages, including low-resource ones. Specifically, we introducea lightweight adapter set to enhance MLLMs with cross-lingual entity alignment and facts from MLKGs for many languages. Experiments on common benchmarks show that such enhancement benefits both MLLMs and MLKGs, achieving: (1) comparable or improved performance for knowledge graph completion and entity alignment relative to baselines, especially for low-resource languages (for which knowledge graphs are unavailable); and (2) improved MLLM performance on language understanding tasks that require multilingual factual knowledge; all while maintaining performance on other general language tasks.</abstract>
<identifier type="citekey">hou-etal-2022-adapters</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.287</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.287</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3902</start>
<end>3917</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapters for Enhanced Modeling of Multilingual Knowledge and Text
%A Hou, Yifan
%A Jiao, Wenxiang
%A Liu, Meizhen
%A Allen, Carl
%A Tu, Zhaopeng
%A Sachan, Mrinmaya
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F hou-etal-2022-adapters
%X Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned. Language models have recently been extended to multilingual language models (MLLMs), enabling knowledge to be learned across hundreds of languages. Meanwhile, knowledge graphs contain facts in an explicit triple format, which require careful and costly curation and are only available in a few high-resource languages, restricting their research and application. To address these issues, we propose to enhance MLLMs with knowledge from multilingual knowledge graphs (MLKGs) so as to tackle language and knowledge graph tasks across many languages, including low-resource ones. Specifically, we introducea lightweight adapter set to enhance MLLMs with cross-lingual entity alignment and facts from MLKGs for many languages. Experiments on common benchmarks show that such enhancement benefits both MLLMs and MLKGs, achieving: (1) comparable or improved performance for knowledge graph completion and entity alignment relative to baselines, especially for low-resource languages (for which knowledge graphs are unavailable); and (2) improved MLLM performance on language understanding tasks that require multilingual factual knowledge; all while maintaining performance on other general language tasks.
%R 10.18653/v1/2022.findings-emnlp.287
%U https://aclanthology.org/2022.findings-emnlp.287
%U https://doi.org/10.18653/v1/2022.findings-emnlp.287
%P 3902-3917
Markdown (Informal)
[Adapters for Enhanced Modeling of Multilingual Knowledge and Text](https://aclanthology.org/2022.findings-emnlp.287) (Hou et al., Findings 2022)
ACL