@inproceedings{finch-etal-2021-went,
title = "What Went Wrong? Explaining Overall Dialogue Quality through Utterance-Level Impacts",
author = "Finch, James D. and
Finch, Sarah E. and
Choi, Jinho D.",
editor = "Papangelis, Alexandros and
Budzianowski, Pawe{\l} and
Liu, Bing and
Nouri, Elnaz and
Rastogi, Abhinav and
Chen, Yun-Nung",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4convai-1.9/",
doi = "10.18653/v1/2021.nlp4convai-1.9",
pages = "93--101",
abstract = "Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to automated analysis of conversation logs that learns the relationship between user-system interactions and overall dialogue quality. Unlike prior work on utterance-level quality prediction, our approach learns the impact of each interaction from the overall user rating without utterance-level annotation, allowing resultant model conclusions to be derived on the basis of empirical evidence and at low cost. Our model identifies interactions that have a strong correlation with the overall dialogue quality in a chatbot setting. Experiments show that the automated analysis from our model agrees with expert judgments, making this work the first to show that such weakly-supervised learning of utterance-level quality prediction is highly achievable."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="finch-etal-2021-went">
<titleInfo>
<title>What Went Wrong? Explaining Overall Dialogue Quality through Utterance-Level Impacts</title>
</titleInfo>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Budzianowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elnaz</namePart>
<namePart type="family">Nouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to automated analysis of conversation logs that learns the relationship between user-system interactions and overall dialogue quality. Unlike prior work on utterance-level quality prediction, our approach learns the impact of each interaction from the overall user rating without utterance-level annotation, allowing resultant model conclusions to be derived on the basis of empirical evidence and at low cost. Our model identifies interactions that have a strong correlation with the overall dialogue quality in a chatbot setting. Experiments show that the automated analysis from our model agrees with expert judgments, making this work the first to show that such weakly-supervised learning of utterance-level quality prediction is highly achievable.</abstract>
<identifier type="citekey">finch-etal-2021-went</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4convai-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4convai-1.9/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>93</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Went Wrong? Explaining Overall Dialogue Quality through Utterance-Level Impacts
%A Finch, James D.
%A Finch, Sarah E.
%A Choi, Jinho D.
%Y Papangelis, Alexandros
%Y Budzianowski, Paweł
%Y Liu, Bing
%Y Nouri, Elnaz
%Y Rastogi, Abhinav
%Y Chen, Yun-Nung
%S Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F finch-etal-2021-went
%X Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to automated analysis of conversation logs that learns the relationship between user-system interactions and overall dialogue quality. Unlike prior work on utterance-level quality prediction, our approach learns the impact of each interaction from the overall user rating without utterance-level annotation, allowing resultant model conclusions to be derived on the basis of empirical evidence and at low cost. Our model identifies interactions that have a strong correlation with the overall dialogue quality in a chatbot setting. Experiments show that the automated analysis from our model agrees with expert judgments, making this work the first to show that such weakly-supervised learning of utterance-level quality prediction is highly achievable.
%R 10.18653/v1/2021.nlp4convai-1.9
%U https://aclanthology.org/2021.nlp4convai-1.9/
%U https://doi.org/10.18653/v1/2021.nlp4convai-1.9
%P 93-101
Markdown (Informal)
[What Went Wrong? Explaining Overall Dialogue Quality through Utterance-Level Impacts](https://aclanthology.org/2021.nlp4convai-1.9/) (Finch et al., NLP4ConvAI 2021)
ACL