@inproceedings{wu-etal-2022-towards-context,
title = "Towards In-Context Non-Expert Evaluation of Reflection Generation for Counselling Conversations",
author = "Wu, Zixiu and
Balloccu, Simone and
Helaoui, Rim and
Recupero, Diego Reforgiato and
Riboni, Daniele",
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-1.9",
doi = "10.18653/v1/2022.gem-1.9",
pages = "116--124",
abstract = "Reflection is an essential counselling strategy, where the therapist listens actively and responds with their own interpretation of the client{'}s words. Recent work leveraged pre-trained language models (PLMs) to approach reflection generation as a promising tool to aid counsellor training. However, those studies used limited dialogue context for modelling and simplistic error analysis for human evaluation. In this work, we take the first step towards addressing those limitations. First, we fine-tune PLMs on longer dialogue contexts for reflection generation. Then, we collect free-text error descriptions from non-experts about generated reflections, identify common patterns among them, and accordingly establish discrete error categories using thematic analysis. Based on this scheme, we plan for future work a mass non-expert error annotation phase for generated reflections followed by an expert-based validation phase, namely {``}whether a coherent and consistent response is a good reflection{''}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2022-towards-context">
<titleInfo>
<title>Towards In-Context Non-Expert Evaluation of Reflection Generation for Counselling Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zixiu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Balloccu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rim</namePart>
<namePart type="family">Helaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="given">Reforgiato</namePart>
<namePart type="family">Recupero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniele</namePart>
<namePart type="family">Riboni</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>Reflection is an essential counselling strategy, where the therapist listens actively and responds with their own interpretation of the client’s words. Recent work leveraged pre-trained language models (PLMs) to approach reflection generation as a promising tool to aid counsellor training. However, those studies used limited dialogue context for modelling and simplistic error analysis for human evaluation. In this work, we take the first step towards addressing those limitations. First, we fine-tune PLMs on longer dialogue contexts for reflection generation. Then, we collect free-text error descriptions from non-experts about generated reflections, identify common patterns among them, and accordingly establish discrete error categories using thematic analysis. Based on this scheme, we plan for future work a mass non-expert error annotation phase for generated reflections followed by an expert-based validation phase, namely “whether a coherent and consistent response is a good reflection”.</abstract>
<identifier type="citekey">wu-etal-2022-towards-context</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.9</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.9</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>116</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards In-Context Non-Expert Evaluation of Reflection Generation for Counselling Conversations
%A Wu, Zixiu
%A Balloccu, Simone
%A Helaoui, Rim
%A Recupero, Diego Reforgiato
%A Riboni, Daniele
%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 wu-etal-2022-towards-context
%X Reflection is an essential counselling strategy, where the therapist listens actively and responds with their own interpretation of the client’s words. Recent work leveraged pre-trained language models (PLMs) to approach reflection generation as a promising tool to aid counsellor training. However, those studies used limited dialogue context for modelling and simplistic error analysis for human evaluation. In this work, we take the first step towards addressing those limitations. First, we fine-tune PLMs on longer dialogue contexts for reflection generation. Then, we collect free-text error descriptions from non-experts about generated reflections, identify common patterns among them, and accordingly establish discrete error categories using thematic analysis. Based on this scheme, we plan for future work a mass non-expert error annotation phase for generated reflections followed by an expert-based validation phase, namely “whether a coherent and consistent response is a good reflection”.
%R 10.18653/v1/2022.gem-1.9
%U https://aclanthology.org/2022.gem-1.9
%U https://doi.org/10.18653/v1/2022.gem-1.9
%P 116-124
Markdown (Informal)
[Towards In-Context Non-Expert Evaluation of Reflection Generation for Counselling Conversations](https://aclanthology.org/2022.gem-1.9) (Wu et al., GEM 2022)
ACL