@inproceedings{zhang-etal-2024-knowledge-enhanced-pre,
title = "Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval",
author = "Zhang, Hang and
Gong, Yeyun and
Liu, Dayiheng and
Zhang, Shunyu and
He, Xingwei and
Lv, Jiancheng and
Guo, Jian",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.857",
pages = "9810--9821",
abstract = "In recent years, multilingual pre-trained language models (mPLMs) have achieved significant progress in cross-lingual dense retrieval. However, most mPLMs neglect the importance of knowledge. Knowledge always conveys similar semantic concepts in a language-agnostic manner, while query-passage pairs in cross-lingual retrieval also share common factual information. Motivated by this observation, we introduce KEPT, a novel mPLM that effectively leverages knowledge to learn language-agnostic semantic representations. To achieve this, we construct a multilingual knowledge base using hyperlinks and cross-language page alignment data annotated by Wiki. From this knowledge base, we mine intra- and cross-language pairs by extracting symmetrically linked segments and multilingual entity descriptions. Subsequently, we adopt contrastive learning with the mined pairs to pre-train KEPT. We evaluate KEPT on three widely-used benchmarks, considering both zero-shot cross-lingual transfer and supervised multilingual fine-tuning scenarios. Extensive experimental results demonstrate that KEPT achieves strong multilingual and cross-lingual retrieval performance with significant improvements over existing mPLMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-knowledge-enhanced-pre">
<titleInfo>
<title>Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeyun</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayiheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shunyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingwei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiancheng</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, multilingual pre-trained language models (mPLMs) have achieved significant progress in cross-lingual dense retrieval. However, most mPLMs neglect the importance of knowledge. Knowledge always conveys similar semantic concepts in a language-agnostic manner, while query-passage pairs in cross-lingual retrieval also share common factual information. Motivated by this observation, we introduce KEPT, a novel mPLM that effectively leverages knowledge to learn language-agnostic semantic representations. To achieve this, we construct a multilingual knowledge base using hyperlinks and cross-language page alignment data annotated by Wiki. From this knowledge base, we mine intra- and cross-language pairs by extracting symmetrically linked segments and multilingual entity descriptions. Subsequently, we adopt contrastive learning with the mined pairs to pre-train KEPT. We evaluate KEPT on three widely-used benchmarks, considering both zero-shot cross-lingual transfer and supervised multilingual fine-tuning scenarios. Extensive experimental results demonstrate that KEPT achieves strong multilingual and cross-lingual retrieval performance with significant improvements over existing mPLMs.</abstract>
<identifier type="citekey">zhang-etal-2024-knowledge-enhanced-pre</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.857</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9810</start>
<end>9821</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval
%A Zhang, Hang
%A Gong, Yeyun
%A Liu, Dayiheng
%A Zhang, Shunyu
%A He, Xingwei
%A Lv, Jiancheng
%A Guo, Jian
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhang-etal-2024-knowledge-enhanced-pre
%X In recent years, multilingual pre-trained language models (mPLMs) have achieved significant progress in cross-lingual dense retrieval. However, most mPLMs neglect the importance of knowledge. Knowledge always conveys similar semantic concepts in a language-agnostic manner, while query-passage pairs in cross-lingual retrieval also share common factual information. Motivated by this observation, we introduce KEPT, a novel mPLM that effectively leverages knowledge to learn language-agnostic semantic representations. To achieve this, we construct a multilingual knowledge base using hyperlinks and cross-language page alignment data annotated by Wiki. From this knowledge base, we mine intra- and cross-language pairs by extracting symmetrically linked segments and multilingual entity descriptions. Subsequently, we adopt contrastive learning with the mined pairs to pre-train KEPT. We evaluate KEPT on three widely-used benchmarks, considering both zero-shot cross-lingual transfer and supervised multilingual fine-tuning scenarios. Extensive experimental results demonstrate that KEPT achieves strong multilingual and cross-lingual retrieval performance with significant improvements over existing mPLMs.
%U https://aclanthology.org/2024.lrec-main.857
%P 9810-9821
Markdown (Informal)
[Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval](https://aclanthology.org/2024.lrec-main.857) (Zhang et al., LREC-COLING 2024)
ACL
- Hang Zhang, Yeyun Gong, Dayiheng Liu, Shunyu Zhang, Xingwei He, Jiancheng Lv, and Jian Guo. 2024. Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9810–9821, Torino, Italia. ELRA and ICCL.