@inproceedings{svikhnushina-etal-2022-ieval,
title = "i{E}val: Interactive Evaluation Framework for Open-Domain Empathetic Chatbots",
author = "Svikhnushina, Ekaterina and
Filippova, Anastasiia and
Pu, Pearl",
editor = "Lemon, Oliver and
Hakkani-Tur, Dilek and
Li, Junyi Jessy and
Ashrafzadeh, Arash and
Garcia, Daniel Hern{\'a}ndez and
Alikhani, Malihe and
Vandyke, David and
Du{\v{s}}ek, Ond{\v{r}}ej",
booktitle = "Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2022",
address = "Edinburgh, UK",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sigdial-1.41",
doi = "10.18653/v1/2022.sigdial-1.41",
pages = "419--431",
abstract = "Building an empathetic chatbot is an important objective in dialog generation research, with evaluation being one of the most challenging parts. By empathy, we mean the ability to understand and relate to the speakers{'} emotions, and respond to them appropriately. Human evaluation has been considered as the current standard for measuring the performance of open-domain empathetic chatbots. However, existing evaluation procedures suffer from a number of limitations we try to address in our current work. In this paper, we describe iEval, a novel interactive evaluation framework where the person chatting with the bots also rates them on different conversational aspects, as well as ranking them, resulting in greater consistency of the scores. We use iEval to benchmark several state-of-the-art empathetic chatbots, allowing us to discover some intricate details in their performance in different emotional contexts. Based on these results, we present key implications for further improvement of such chatbots. To facilitate other researchers using the iEval framework, we will release our dataset consisting of collected chat logs and human scores.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="svikhnushina-etal-2022-ieval">
<titleInfo>
<title>iEval: Interactive Evaluation Framework for Open-Domain Empathetic Chatbots</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Svikhnushina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasiia</namePart>
<namePart type="family">Filippova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pearl</namePart>
<namePart type="family">Pu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Ashrafzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="given">Hernández</namePart>
<namePart type="family">Garcia</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>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Edinburgh, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building an empathetic chatbot is an important objective in dialog generation research, with evaluation being one of the most challenging parts. By empathy, we mean the ability to understand and relate to the speakers’ emotions, and respond to them appropriately. Human evaluation has been considered as the current standard for measuring the performance of open-domain empathetic chatbots. However, existing evaluation procedures suffer from a number of limitations we try to address in our current work. In this paper, we describe iEval, a novel interactive evaluation framework where the person chatting with the bots also rates them on different conversational aspects, as well as ranking them, resulting in greater consistency of the scores. We use iEval to benchmark several state-of-the-art empathetic chatbots, allowing us to discover some intricate details in their performance in different emotional contexts. Based on these results, we present key implications for further improvement of such chatbots. To facilitate other researchers using the iEval framework, we will release our dataset consisting of collected chat logs and human scores.</abstract>
<identifier type="citekey">svikhnushina-etal-2022-ieval</identifier>
<identifier type="doi">10.18653/v1/2022.sigdial-1.41</identifier>
<location>
<url>https://aclanthology.org/2022.sigdial-1.41</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>419</start>
<end>431</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T iEval: Interactive Evaluation Framework for Open-Domain Empathetic Chatbots
%A Svikhnushina, Ekaterina
%A Filippova, Anastasiia
%A Pu, Pearl
%Y Lemon, Oliver
%Y Hakkani-Tur, Dilek
%Y Li, Junyi Jessy
%Y Ashrafzadeh, Arash
%Y Garcia, Daniel Hernández
%Y Alikhani, Malihe
%Y Vandyke, David
%Y Dušek, Ondřej
%S Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2022
%8 September
%I Association for Computational Linguistics
%C Edinburgh, UK
%F svikhnushina-etal-2022-ieval
%X Building an empathetic chatbot is an important objective in dialog generation research, with evaluation being one of the most challenging parts. By empathy, we mean the ability to understand and relate to the speakers’ emotions, and respond to them appropriately. Human evaluation has been considered as the current standard for measuring the performance of open-domain empathetic chatbots. However, existing evaluation procedures suffer from a number of limitations we try to address in our current work. In this paper, we describe iEval, a novel interactive evaluation framework where the person chatting with the bots also rates them on different conversational aspects, as well as ranking them, resulting in greater consistency of the scores. We use iEval to benchmark several state-of-the-art empathetic chatbots, allowing us to discover some intricate details in their performance in different emotional contexts. Based on these results, we present key implications for further improvement of such chatbots. To facilitate other researchers using the iEval framework, we will release our dataset consisting of collected chat logs and human scores.
%R 10.18653/v1/2022.sigdial-1.41
%U https://aclanthology.org/2022.sigdial-1.41
%U https://doi.org/10.18653/v1/2022.sigdial-1.41
%P 419-431
Markdown (Informal)
[iEval: Interactive Evaluation Framework for Open-Domain Empathetic Chatbots](https://aclanthology.org/2022.sigdial-1.41) (Svikhnushina et al., SIGDIAL 2022)
ACL