@inproceedings{dao-etal-2023-reinforced,
title = "Reinforced Target-driven Conversational Promotion",
author = "Dao, Huy and
Liao, Lizi and
Le, Dung and
Nie, Yuxiang",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.775",
doi = "10.18653/v1/2023.emnlp-main.775",
pages = "12583--12596",
abstract = "The ability to proactively engage with users towards pitching products is highly desired for conversational assistants. However, existing conversational recommendation methods overemphasize on acquiring user preferences while ignore the strategic planning for nudging users towards accepting a designated item. Hence, these methods fail to promote specified items with engaging responses. In this work, we propose a Reinforced Target-driven Conversational Promotion (RTCP) framework for conversational promotion. RTCP integrates short-term and long-term planning via a balanced gating mechanism. Inside which, the dialogue actions are predicted via a knowledge-integrated multi-head attention and guided via reinforcement learning rewards. RTCP then employs action-guided prefix tuning to generate relevant responses. Experimental results demonstrate that our model outperforms state-of-the-art models on both automatic metrics and human evaluation. Moreover, RTCP has a strong capability in quickly adapting to unseen scenarios just by updating prefix parameters without re-training the whole model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dao-etal-2023-reinforced">
<titleInfo>
<title>Reinforced Target-driven Conversational Promotion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huy</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizi</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dung</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiang</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ability to proactively engage with users towards pitching products is highly desired for conversational assistants. However, existing conversational recommendation methods overemphasize on acquiring user preferences while ignore the strategic planning for nudging users towards accepting a designated item. Hence, these methods fail to promote specified items with engaging responses. In this work, we propose a Reinforced Target-driven Conversational Promotion (RTCP) framework for conversational promotion. RTCP integrates short-term and long-term planning via a balanced gating mechanism. Inside which, the dialogue actions are predicted via a knowledge-integrated multi-head attention and guided via reinforcement learning rewards. RTCP then employs action-guided prefix tuning to generate relevant responses. Experimental results demonstrate that our model outperforms state-of-the-art models on both automatic metrics and human evaluation. Moreover, RTCP has a strong capability in quickly adapting to unseen scenarios just by updating prefix parameters without re-training the whole model.</abstract>
<identifier type="citekey">dao-etal-2023-reinforced</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.775</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.775</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12583</start>
<end>12596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reinforced Target-driven Conversational Promotion
%A Dao, Huy
%A Liao, Lizi
%A Le, Dung
%A Nie, Yuxiang
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F dao-etal-2023-reinforced
%X The ability to proactively engage with users towards pitching products is highly desired for conversational assistants. However, existing conversational recommendation methods overemphasize on acquiring user preferences while ignore the strategic planning for nudging users towards accepting a designated item. Hence, these methods fail to promote specified items with engaging responses. In this work, we propose a Reinforced Target-driven Conversational Promotion (RTCP) framework for conversational promotion. RTCP integrates short-term and long-term planning via a balanced gating mechanism. Inside which, the dialogue actions are predicted via a knowledge-integrated multi-head attention and guided via reinforcement learning rewards. RTCP then employs action-guided prefix tuning to generate relevant responses. Experimental results demonstrate that our model outperforms state-of-the-art models on both automatic metrics and human evaluation. Moreover, RTCP has a strong capability in quickly adapting to unseen scenarios just by updating prefix parameters without re-training the whole model.
%R 10.18653/v1/2023.emnlp-main.775
%U https://aclanthology.org/2023.emnlp-main.775
%U https://doi.org/10.18653/v1/2023.emnlp-main.775
%P 12583-12596
Markdown (Informal)
[Reinforced Target-driven Conversational Promotion](https://aclanthology.org/2023.emnlp-main.775) (Dao et al., EMNLP 2023)
ACL
- Huy Dao, Lizi Liao, Dung Le, and Yuxiang Nie. 2023. Reinforced Target-driven Conversational Promotion. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12583–12596, Singapore. Association for Computational Linguistics.