@inproceedings{gupta-etal-2021-controlling,
title = "Controlling Dialogue Generation with Semantic Exemplars",
author = "Gupta, Prakhar and
Bigham, Jeffrey and
Tsvetkov, Yulia and
Pavel, Amy",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.240",
doi = "10.18653/v1/2021.naacl-main.240",
pages = "3018--3029",
abstract = "Dialogue systems pretrained with large language models generate locally coherent responses, but lack fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is exemplar-based generation, in which models edit exemplar responses that are retrieved from training data, or hand-written to strategically address discourse-level goals, to fit new dialogue contexts. We present an Exemplar-based Dialogue Generation model, EDGE, that uses the semantic frames present in exemplar responses to guide response generation. We show that controlling dialogue generation based on the semantic frames of exemplars improves the coherence of generated responses, while preserving semantic meaning and conversation goals present in exemplar responses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2021-controlling">
<titleInfo>
<title>Controlling Dialogue Generation with Semantic Exemplars</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prakhar</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Bigham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amy</namePart>
<namePart type="family">Pavel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue systems pretrained with large language models generate locally coherent responses, but lack fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is exemplar-based generation, in which models edit exemplar responses that are retrieved from training data, or hand-written to strategically address discourse-level goals, to fit new dialogue contexts. We present an Exemplar-based Dialogue Generation model, EDGE, that uses the semantic frames present in exemplar responses to guide response generation. We show that controlling dialogue generation based on the semantic frames of exemplars improves the coherence of generated responses, while preserving semantic meaning and conversation goals present in exemplar responses.</abstract>
<identifier type="citekey">gupta-etal-2021-controlling</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.240</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.240</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3018</start>
<end>3029</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Controlling Dialogue Generation with Semantic Exemplars
%A Gupta, Prakhar
%A Bigham, Jeffrey
%A Tsvetkov, Yulia
%A Pavel, Amy
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F gupta-etal-2021-controlling
%X Dialogue systems pretrained with large language models generate locally coherent responses, but lack fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is exemplar-based generation, in which models edit exemplar responses that are retrieved from training data, or hand-written to strategically address discourse-level goals, to fit new dialogue contexts. We present an Exemplar-based Dialogue Generation model, EDGE, that uses the semantic frames present in exemplar responses to guide response generation. We show that controlling dialogue generation based on the semantic frames of exemplars improves the coherence of generated responses, while preserving semantic meaning and conversation goals present in exemplar responses.
%R 10.18653/v1/2021.naacl-main.240
%U https://aclanthology.org/2021.naacl-main.240
%U https://doi.org/10.18653/v1/2021.naacl-main.240
%P 3018-3029
Markdown (Informal)
[Controlling Dialogue Generation with Semantic Exemplars](https://aclanthology.org/2021.naacl-main.240) (Gupta et al., NAACL 2021)
ACL
- Prakhar Gupta, Jeffrey Bigham, Yulia Tsvetkov, and Amy Pavel. 2021. Controlling Dialogue Generation with Semantic Exemplars. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3018–3029, Online. Association for Computational Linguistics.