@inproceedings{chernyavskiy-ilvovsky-2023-transformer,
title = "Transformer-based Multi-Party Conversation Generation using Dialogue Discourse Acts Planning",
author = "Chernyavskiy, Alexander and
Ilvovsky, Dmitry",
editor = "Stoyanchev, Svetlana and
Joty, Shafiq and
Schlangen, David and
Dusek, Ondrej and
Kennington, Casey and
Alikhani, Malihe",
booktitle = "Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigdial-1.48",
doi = "10.18653/v1/2023.sigdial-1.48",
pages = "519--529",
abstract = "Recent transformer-based approaches to multi-party conversation generation may produce syntactically coherent but discursively inconsistent dialogues in some cases. To address this issue, we propose an approach to integrate a dialogue act planning stage into the end-to-end transformer-based generation pipeline. This approach consists of a transformer fine-tuning procedure based on linearized dialogue representations that include special discourse tokens. The obtained results demonstrate that incorporating discourse tokens into training sequences is sufficient to significantly improve dialogue consistency and overall generation quality. The suggested approach performs well, including for automatically annotated data. Apart from that, it is observed that increasing the weight of the discourse planning task in the loss function accelerates learning convergence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chernyavskiy-ilvovsky-2023-transformer">
<titleInfo>
<title>Transformer-based Multi-Party Conversation Generation using Dialogue Discourse Acts Planning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Chernyavskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ilvovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Stoyanchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent transformer-based approaches to multi-party conversation generation may produce syntactically coherent but discursively inconsistent dialogues in some cases. To address this issue, we propose an approach to integrate a dialogue act planning stage into the end-to-end transformer-based generation pipeline. This approach consists of a transformer fine-tuning procedure based on linearized dialogue representations that include special discourse tokens. The obtained results demonstrate that incorporating discourse tokens into training sequences is sufficient to significantly improve dialogue consistency and overall generation quality. The suggested approach performs well, including for automatically annotated data. Apart from that, it is observed that increasing the weight of the discourse planning task in the loss function accelerates learning convergence.</abstract>
<identifier type="citekey">chernyavskiy-ilvovsky-2023-transformer</identifier>
<identifier type="doi">10.18653/v1/2023.sigdial-1.48</identifier>
<location>
<url>https://aclanthology.org/2023.sigdial-1.48</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>519</start>
<end>529</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transformer-based Multi-Party Conversation Generation using Dialogue Discourse Acts Planning
%A Chernyavskiy, Alexander
%A Ilvovsky, Dmitry
%Y Stoyanchev, Svetlana
%Y Joty, Shafiq
%Y Schlangen, David
%Y Dusek, Ondrej
%Y Kennington, Casey
%Y Alikhani, Malihe
%S Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F chernyavskiy-ilvovsky-2023-transformer
%X Recent transformer-based approaches to multi-party conversation generation may produce syntactically coherent but discursively inconsistent dialogues in some cases. To address this issue, we propose an approach to integrate a dialogue act planning stage into the end-to-end transformer-based generation pipeline. This approach consists of a transformer fine-tuning procedure based on linearized dialogue representations that include special discourse tokens. The obtained results demonstrate that incorporating discourse tokens into training sequences is sufficient to significantly improve dialogue consistency and overall generation quality. The suggested approach performs well, including for automatically annotated data. Apart from that, it is observed that increasing the weight of the discourse planning task in the loss function accelerates learning convergence.
%R 10.18653/v1/2023.sigdial-1.48
%U https://aclanthology.org/2023.sigdial-1.48
%U https://doi.org/10.18653/v1/2023.sigdial-1.48
%P 519-529
Markdown (Informal)
[Transformer-based Multi-Party Conversation Generation using Dialogue Discourse Acts Planning](https://aclanthology.org/2023.sigdial-1.48) (Chernyavskiy & Ilvovsky, SIGDIAL 2023)
ACL