@inproceedings{wang-etal-2023-retrieval,
title = "Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models",
author = "Wang, Rui and
Bao, Jianzhu and
Mi, Fei and
Chen, Yi and
Wang, Hongru and
Wang, Yasheng and
Li, Yitong and
Shang, Lifeng and
Wong, Kam-Fai and
Xu, Ruifeng",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.364",
doi = "10.18653/v1/2023.acl-long.364",
pages = "6608--6619",
abstract = "Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models{'} knowledge w.r.t. this domain without costly annotation. We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-of-the-art retrieval-free methods, and it achieves comparable performance compared to retrieval-augmented methods while being better, and cheaper at domain transfer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-retrieval">
<titleInfo>
<title>Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianzhu</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Mi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongru</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yitong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</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 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models’ knowledge w.r.t. this domain without costly annotation. We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-of-the-art retrieval-free methods, and it achieves comparable performance compared to retrieval-augmented methods while being better, and cheaper at domain transfer.</abstract>
<identifier type="citekey">wang-etal-2023-retrieval</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.364</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.364</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6608</start>
<end>6619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models
%A Wang, Rui
%A Bao, Jianzhu
%A Mi, Fei
%A Chen, Yi
%A Wang, Hongru
%A Wang, Yasheng
%A Li, Yitong
%A Shang, Lifeng
%A Wong, Kam-Fai
%A Xu, Ruifeng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-retrieval
%X Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models’ knowledge w.r.t. this domain without costly annotation. We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-of-the-art retrieval-free methods, and it achieves comparable performance compared to retrieval-augmented methods while being better, and cheaper at domain transfer.
%R 10.18653/v1/2023.acl-long.364
%U https://aclanthology.org/2023.acl-long.364
%U https://doi.org/10.18653/v1/2023.acl-long.364
%P 6608-6619
Markdown (Informal)
[Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models](https://aclanthology.org/2023.acl-long.364) (Wang et al., ACL 2023)
ACL
- Rui Wang, Jianzhu Bao, Fei Mi, Yi Chen, Hongru Wang, Yasheng Wang, Yitong Li, Lifeng Shang, Kam-Fai Wong, and Ruifeng Xu. 2023. Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6608–6619, Toronto, Canada. Association for Computational Linguistics.