@inproceedings{gupta-etal-2022-answerability,
title = "Answerability: A custom metric for evaluating chatbot performance",
author = "Gupta, Pranav and
Rajasekar, Anand A. and
Patel, Amisha and
Kulkarni, Mandar and
Sunell, Alexander and
Kim, Kyung and
Ganapathy, Krishnan and
Trivedi, Anusua",
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-1.27",
doi = "10.18653/v1/2022.gem-1.27",
pages = "316--325",
abstract = "Most commercial conversational AI products in domains spanning e-commerce, health care, finance, and education involve a hierarchy of NLP models that perform a variety of tasks such as classification, entity recognition, question-answering, sentiment detection, semantic text similarity, and so on. Despite our understanding of each of the constituent models, we do not have a clear view as to how these models affect the overall platform metrics. To bridge this gap, we define a metric known as answerability, which penalizes not only irrelevant or incorrect chatbot responses but also unhelpful responses that do not serve the chatbot{'}s purpose despite being correct or relevant. Additionally, we describe a formula-based mathematical framework to relate individual model metrics to the answerability metric. We also describe a modeling approach for predicting a chatbot{'}s answerability to a user question and its corresponding chatbot response.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2022-answerability">
<titleInfo>
<title>Answerability: A custom metric for evaluating chatbot performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Rajasekar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amisha</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mandar</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Sunell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishnan</namePart>
<namePart type="family">Ganapathy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anusua</namePart>
<namePart type="family">Trivedi</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>Most commercial conversational AI products in domains spanning e-commerce, health care, finance, and education involve a hierarchy of NLP models that perform a variety of tasks such as classification, entity recognition, question-answering, sentiment detection, semantic text similarity, and so on. Despite our understanding of each of the constituent models, we do not have a clear view as to how these models affect the overall platform metrics. To bridge this gap, we define a metric known as answerability, which penalizes not only irrelevant or incorrect chatbot responses but also unhelpful responses that do not serve the chatbot’s purpose despite being correct or relevant. Additionally, we describe a formula-based mathematical framework to relate individual model metrics to the answerability metric. We also describe a modeling approach for predicting a chatbot’s answerability to a user question and its corresponding chatbot response.</abstract>
<identifier type="citekey">gupta-etal-2022-answerability</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.27</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.27</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>316</start>
<end>325</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Answerability: A custom metric for evaluating chatbot performance
%A Gupta, Pranav
%A Rajasekar, Anand A.
%A Patel, Amisha
%A Kulkarni, Mandar
%A Sunell, Alexander
%A Kim, Kyung
%A Ganapathy, Krishnan
%A Trivedi, Anusua
%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 gupta-etal-2022-answerability
%X Most commercial conversational AI products in domains spanning e-commerce, health care, finance, and education involve a hierarchy of NLP models that perform a variety of tasks such as classification, entity recognition, question-answering, sentiment detection, semantic text similarity, and so on. Despite our understanding of each of the constituent models, we do not have a clear view as to how these models affect the overall platform metrics. To bridge this gap, we define a metric known as answerability, which penalizes not only irrelevant or incorrect chatbot responses but also unhelpful responses that do not serve the chatbot’s purpose despite being correct or relevant. Additionally, we describe a formula-based mathematical framework to relate individual model metrics to the answerability metric. We also describe a modeling approach for predicting a chatbot’s answerability to a user question and its corresponding chatbot response.
%R 10.18653/v1/2022.gem-1.27
%U https://aclanthology.org/2022.gem-1.27
%U https://doi.org/10.18653/v1/2022.gem-1.27
%P 316-325
Markdown (Informal)
[Answerability: A custom metric for evaluating chatbot performance](https://aclanthology.org/2022.gem-1.27) (Gupta et al., GEM 2022)
ACL
- Pranav Gupta, Anand A. Rajasekar, Amisha Patel, Mandar Kulkarni, Alexander Sunell, Kyung Kim, Krishnan Ganapathy, and Anusua Trivedi. 2022. Answerability: A custom metric for evaluating chatbot performance. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 316–325, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.