@inproceedings{jansen-etal-2022-controllable,
title = "Controllable Text Generation for All Ages: Evaluating a Plug-and-Play Approach to Age-Adapted Dialogue",
author = "Jansen, Lennert and
Laichter, {\v{S}}t{\v{e}}p{\'a}n Lars and
Sinclair, Arabella and
van der Goot, Margot and
Fernandez, Raquel and
Pezzelle, Sandro",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.14",
doi = "10.18653/v1/2022.gem-1.14",
pages = "172--188",
abstract = "To be trusted and perceived as natural and coherent, conversational systems must adapt to the language of their users. While personalized dialogue is a promising direction, controlling generation for fine-grained language features remains a challenge in this approach. A recent line of research showed the effectiveness of leveraging pre-trained language models toward adapting to a text{'}s topic or sentiment. In this study, we build on these approaches and focus on a higher-level dimension of language variation: speakers{'} age. We frame the task as a dialogue response generation, and test methods based on bag-of-words (BoW) and neural discriminators (Disc) to condition the output of GPT-2 and DialoGPT without altering the parameters of the language models. We show that Disc models achieve a higher degree of detectable control than BoW models based on automatic evaluation. In contrast, humans can partially detect age differences in BoW but not Disc responses. Since BoW responses are deemed better than Disc ones by humans, simple controllable methods thus appear to be a better tradeoff between adaptation and language quality. Our work confirms the challenges of adapting to higher-level dimensions of language variation. Moreover, it highlights the need to evaluate natural language generation thoroughly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jansen-etal-2022-controllable">
<titleInfo>
<title>Controllable Text Generation for All Ages: Evaluating a Plug-and-Play Approach to Age-Adapted Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lennert</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Štěpán</namePart>
<namePart type="given">Lars</namePart>
<namePart type="family">Laichter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arabella</namePart>
<namePart type="family">Sinclair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandro</namePart>
<namePart type="family">Pezzelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To be trusted and perceived as natural and coherent, conversational systems must adapt to the language of their users. While personalized dialogue is a promising direction, controlling generation for fine-grained language features remains a challenge in this approach. A recent line of research showed the effectiveness of leveraging pre-trained language models toward adapting to a text’s topic or sentiment. In this study, we build on these approaches and focus on a higher-level dimension of language variation: speakers’ age. We frame the task as a dialogue response generation, and test methods based on bag-of-words (BoW) and neural discriminators (Disc) to condition the output of GPT-2 and DialoGPT without altering the parameters of the language models. We show that Disc models achieve a higher degree of detectable control than BoW models based on automatic evaluation. In contrast, humans can partially detect age differences in BoW but not Disc responses. Since BoW responses are deemed better than Disc ones by humans, simple controllable methods thus appear to be a better tradeoff between adaptation and language quality. Our work confirms the challenges of adapting to higher-level dimensions of language variation. Moreover, it highlights the need to evaluate natural language generation thoroughly.</abstract>
<identifier type="citekey">jansen-etal-2022-controllable</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.14</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.14</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>172</start>
<end>188</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Controllable Text Generation for All Ages: Evaluating a Plug-and-Play Approach to Age-Adapted Dialogue
%A Jansen, Lennert
%A Laichter, Štěpán Lars
%A Sinclair, Arabella
%A van der Goot, Margot
%A Fernandez, Raquel
%A Pezzelle, Sandro
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F jansen-etal-2022-controllable
%X To be trusted and perceived as natural and coherent, conversational systems must adapt to the language of their users. While personalized dialogue is a promising direction, controlling generation for fine-grained language features remains a challenge in this approach. A recent line of research showed the effectiveness of leveraging pre-trained language models toward adapting to a text’s topic or sentiment. In this study, we build on these approaches and focus on a higher-level dimension of language variation: speakers’ age. We frame the task as a dialogue response generation, and test methods based on bag-of-words (BoW) and neural discriminators (Disc) to condition the output of GPT-2 and DialoGPT without altering the parameters of the language models. We show that Disc models achieve a higher degree of detectable control than BoW models based on automatic evaluation. In contrast, humans can partially detect age differences in BoW but not Disc responses. Since BoW responses are deemed better than Disc ones by humans, simple controllable methods thus appear to be a better tradeoff between adaptation and language quality. Our work confirms the challenges of adapting to higher-level dimensions of language variation. Moreover, it highlights the need to evaluate natural language generation thoroughly.
%R 10.18653/v1/2022.gem-1.14
%U https://aclanthology.org/2022.gem-1.14
%U https://doi.org/10.18653/v1/2022.gem-1.14
%P 172-188
Markdown (Informal)
[Controllable Text Generation for All Ages: Evaluating a Plug-and-Play Approach to Age-Adapted Dialogue](https://aclanthology.org/2022.gem-1.14) (Jansen et al., GEM 2022)
ACL
- Lennert Jansen, Štěpán Lars Laichter, Arabella Sinclair, Margot van der Goot, Raquel Fernandez, and Sandro Pezzelle. 2022. Controllable Text Generation for All Ages: Evaluating a Plug-and-Play Approach to Age-Adapted Dialogue. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 172–188, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.