@inproceedings{vazquez-risco-etal-2024-knowledge,
title = "Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain {NLG}",
author = "Vazquez Risco, Alain and
Ramirez, Angela Maria and
Pullabhotla, Neha and
Qiang, Nan and
Zhang, Haoran and
Walker, Marilyn and
Torres, Maria Ines",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.7",
doi = "10.18653/v1/2024.sigdial-1.7",
pages = "78--91",
abstract = "Open domain spoken dialogue systems need to controllably generate many different dialogue acts (DAs) to allow Natural Language Generation (NLG) to create interesting and engaging conversational interactions with users. We aim to create an NLG engine that can produce a variety of DAs that make substantive knowledge-grounded contributions to a conversation. Training such an NLG typically requires dialogue corpora that are labelled for DAs, which are expensive to produce and vulnerable to quality issues. Here, we present a prompt-based learning approach to transfer DAs from one domain, video games, to 7 new domains. For each novel domain, we first crawl WikiData to create Meaning Representations that systematically vary both the number of attributes and hops on the WikiData Knowledge Graph. The proposed method involves a self-training step to create prompt examples for each domain followed by an overgeneration and ranking step. The result is a novel, high-quality dataset, Wiki-Dialogue, of 71K knowledge-grounded utterances, covering 9 DAs and the Art, Movies, Music, Sports, TV, Animal, and Boardgames domains, whose combined DA and semantic accuracy is 89{\%}. We assess the corpus quality using both automatic and human evaluations and find it high. The corpus is found to be safe, lexically rich, and large in vocabulary, when compared to similar datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vazquez-risco-etal-2024-knowledge">
<titleInfo>
<title>Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alain</namePart>
<namePart type="family">Vazquez Risco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Ramirez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neha</namePart>
<namePart type="family">Pullabhotla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Qiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Ines</namePart>
<namePart type="family">Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open domain spoken dialogue systems need to controllably generate many different dialogue acts (DAs) to allow Natural Language Generation (NLG) to create interesting and engaging conversational interactions with users. We aim to create an NLG engine that can produce a variety of DAs that make substantive knowledge-grounded contributions to a conversation. Training such an NLG typically requires dialogue corpora that are labelled for DAs, which are expensive to produce and vulnerable to quality issues. Here, we present a prompt-based learning approach to transfer DAs from one domain, video games, to 7 new domains. For each novel domain, we first crawl WikiData to create Meaning Representations that systematically vary both the number of attributes and hops on the WikiData Knowledge Graph. The proposed method involves a self-training step to create prompt examples for each domain followed by an overgeneration and ranking step. The result is a novel, high-quality dataset, Wiki-Dialogue, of 71K knowledge-grounded utterances, covering 9 DAs and the Art, Movies, Music, Sports, TV, Animal, and Boardgames domains, whose combined DA and semantic accuracy is 89%. We assess the corpus quality using both automatic and human evaluations and find it high. The corpus is found to be safe, lexically rich, and large in vocabulary, when compared to similar datasets.</abstract>
<identifier type="citekey">vazquez-risco-etal-2024-knowledge</identifier>
<identifier type="doi">10.18653/v1/2024.sigdial-1.7</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.7</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>78</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG
%A Vazquez Risco, Alain
%A Ramirez, Angela Maria
%A Pullabhotla, Neha
%A Qiang, Nan
%A Zhang, Haoran
%A Walker, Marilyn
%A Torres, Maria Ines
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F vazquez-risco-etal-2024-knowledge
%X Open domain spoken dialogue systems need to controllably generate many different dialogue acts (DAs) to allow Natural Language Generation (NLG) to create interesting and engaging conversational interactions with users. We aim to create an NLG engine that can produce a variety of DAs that make substantive knowledge-grounded contributions to a conversation. Training such an NLG typically requires dialogue corpora that are labelled for DAs, which are expensive to produce and vulnerable to quality issues. Here, we present a prompt-based learning approach to transfer DAs from one domain, video games, to 7 new domains. For each novel domain, we first crawl WikiData to create Meaning Representations that systematically vary both the number of attributes and hops on the WikiData Knowledge Graph. The proposed method involves a self-training step to create prompt examples for each domain followed by an overgeneration and ranking step. The result is a novel, high-quality dataset, Wiki-Dialogue, of 71K knowledge-grounded utterances, covering 9 DAs and the Art, Movies, Music, Sports, TV, Animal, and Boardgames domains, whose combined DA and semantic accuracy is 89%. We assess the corpus quality using both automatic and human evaluations and find it high. The corpus is found to be safe, lexically rich, and large in vocabulary, when compared to similar datasets.
%R 10.18653/v1/2024.sigdial-1.7
%U https://aclanthology.org/2024.sigdial-1.7
%U https://doi.org/10.18653/v1/2024.sigdial-1.7
%P 78-91
Markdown (Informal)
[Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG](https://aclanthology.org/2024.sigdial-1.7) (Vazquez Risco et al., SIGDIAL 2024)
ACL