@inproceedings{li-etal-2023-triplet,
title = "Triplet-Free Knowledge-Guided Response Generation",
author = "Li, Dongming and
Liu, Jianfeng and
Wang, Baoyuan",
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.815",
doi = "10.18653/v1/2023.findings-acl.815",
pages = "12881--12899",
abstract = "Generating vivid and informative responses (e.g., comments for social posts and utterances for dialogues) is challenging without giving relevant knowledge. Prior works focus on constructing the {''}latent{''} knowledge first and then learning how to {''}ground{''} it based on pseudo (context, knowledge, response) triplets. However, the retrieval between real responses and their latent knowledge is difficult in nature. In this paper, instead of focusing on how to ground knowledge given the responses, we take a different perspective to optimize the final responses for given guided knowledge directly. This allows us to re-formulate the entire problem in a simplified yet more scalable way. Specifically, we pretrain a response language model (LM) to measure the relevance and consistency between any context and response, then use search engines to collect the top-ranked passages to serve as the guiding knowledge without explicitly optimizing the {`}{`}best{''} latent knowledge that corresponds to a given response. The final response generation model is trained through reinforcement learning by taking both the response LM prior and knowledge-injection rate as rewards. For better evaluations, we construct a new Chinese benchmark, {''}IceKC{''}, using fresh multimodal online social posts. Both automatic evaluations and human evaluations show our zero-resource approach performs significantly better than prior works.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-triplet">
<titleInfo>
<title>Triplet-Free Knowledge-Guided Response Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongming</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoyuan</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>Generating vivid and informative responses (e.g., comments for social posts and utterances for dialogues) is challenging without giving relevant knowledge. Prior works focus on constructing the ”latent” knowledge first and then learning how to ”ground” it based on pseudo (context, knowledge, response) triplets. However, the retrieval between real responses and their latent knowledge is difficult in nature. In this paper, instead of focusing on how to ground knowledge given the responses, we take a different perspective to optimize the final responses for given guided knowledge directly. This allows us to re-formulate the entire problem in a simplified yet more scalable way. Specifically, we pretrain a response language model (LM) to measure the relevance and consistency between any context and response, then use search engines to collect the top-ranked passages to serve as the guiding knowledge without explicitly optimizing the “best” latent knowledge that corresponds to a given response. The final response generation model is trained through reinforcement learning by taking both the response LM prior and knowledge-injection rate as rewards. For better evaluations, we construct a new Chinese benchmark, ”IceKC”, using fresh multimodal online social posts. Both automatic evaluations and human evaluations show our zero-resource approach performs significantly better than prior works.</abstract>
<identifier type="citekey">li-etal-2023-triplet</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.815</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.815</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12881</start>
<end>12899</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Triplet-Free Knowledge-Guided Response Generation
%A Li, Dongming
%A Liu, Jianfeng
%A Wang, Baoyuan
%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 li-etal-2023-triplet
%X Generating vivid and informative responses (e.g., comments for social posts and utterances for dialogues) is challenging without giving relevant knowledge. Prior works focus on constructing the ”latent” knowledge first and then learning how to ”ground” it based on pseudo (context, knowledge, response) triplets. However, the retrieval between real responses and their latent knowledge is difficult in nature. In this paper, instead of focusing on how to ground knowledge given the responses, we take a different perspective to optimize the final responses for given guided knowledge directly. This allows us to re-formulate the entire problem in a simplified yet more scalable way. Specifically, we pretrain a response language model (LM) to measure the relevance and consistency between any context and response, then use search engines to collect the top-ranked passages to serve as the guiding knowledge without explicitly optimizing the “best” latent knowledge that corresponds to a given response. The final response generation model is trained through reinforcement learning by taking both the response LM prior and knowledge-injection rate as rewards. For better evaluations, we construct a new Chinese benchmark, ”IceKC”, using fresh multimodal online social posts. Both automatic evaluations and human evaluations show our zero-resource approach performs significantly better than prior works.
%R 10.18653/v1/2023.findings-acl.815
%U https://aclanthology.org/2023.findings-acl.815
%U https://doi.org/10.18653/v1/2023.findings-acl.815
%P 12881-12899
Markdown (Informal)
[Triplet-Free Knowledge-Guided Response Generation](https://aclanthology.org/2023.findings-acl.815) (Li et al., Findings 2023)
ACL
- Dongming Li, Jianfeng Liu, and Baoyuan Wang. 2023. Triplet-Free Knowledge-Guided Response Generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12881–12899, Toronto, Canada. Association for Computational Linguistics.