@inproceedings{deriu-etal-2020-spot,
title = "Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems",
author = {Deriu, Jan and
Tuggener, Don and
von D{\"a}niken, Pius and
Campos, Jon Ander and
Rodrigo, Alvaro and
Belkacem, Thiziri and
Soroa, Aitor and
Agirre, Eneko and
Cieliebak, Mark},
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.326",
doi = "10.18653/v1/2020.emnlp-main.326",
pages = "3971--3984",
abstract = "The lack of time efficient and reliable evalu-ation methods is hampering the development of conversational dialogue systems (chat bots). Evaluations that require humans to converse with chat bots are time and cost intensive, put high cognitive demands on the human judges, and tend to yield low quality results. In this work, we introduce Spot The Bot, a cost-efficient and robust evaluation framework that replaces human-bot conversations with conversations between bots. Human judges then only annotate for each entity in a conversation whether they think it is human or not (assuming there are humans participants in these conversations). These annotations then allow us to rank chat bots regarding their ability to mimic conversational behaviour of humans. Since we expect that all bots are eventually recognized as such, we incorporate a metric that measures which chat bot is able to uphold human-like be-havior the longest, i.e.Survival Analysis. This metric has the ability to correlate a bot{'}s performance to certain of its characteristics (e.g.fluency or sensibleness), yielding interpretable results. The comparably low cost of our frame-work allows for frequent evaluations of chatbots during their evaluation cycle. We empirically validate our claims by applying Spot The Bot to three domains, evaluating several state-of-the-art chat bots, and drawing comparisonsto related work. The framework is released asa ready-to-use tool.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deriu-etal-2020-spot">
<titleInfo>
<title>Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Deriu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Don</namePart>
<namePart type="family">Tuggener</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pius</namePart>
<namePart type="family">von Däniken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="given">Ander</namePart>
<namePart type="family">Campos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alvaro</namePart>
<namePart type="family">Rodrigo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiziri</namePart>
<namePart type="family">Belkacem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Cieliebak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>The lack of time efficient and reliable evalu-ation methods is hampering the development of conversational dialogue systems (chat bots). Evaluations that require humans to converse with chat bots are time and cost intensive, put high cognitive demands on the human judges, and tend to yield low quality results. In this work, we introduce Spot The Bot, a cost-efficient and robust evaluation framework that replaces human-bot conversations with conversations between bots. Human judges then only annotate for each entity in a conversation whether they think it is human or not (assuming there are humans participants in these conversations). These annotations then allow us to rank chat bots regarding their ability to mimic conversational behaviour of humans. Since we expect that all bots are eventually recognized as such, we incorporate a metric that measures which chat bot is able to uphold human-like be-havior the longest, i.e.Survival Analysis. This metric has the ability to correlate a bot’s performance to certain of its characteristics (e.g.fluency or sensibleness), yielding interpretable results. The comparably low cost of our frame-work allows for frequent evaluations of chatbots during their evaluation cycle. We empirically validate our claims by applying Spot The Bot to three domains, evaluating several state-of-the-art chat bots, and drawing comparisonsto related work. The framework is released asa ready-to-use tool.</abstract>
<identifier type="citekey">deriu-etal-2020-spot</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.326</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.326</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3971</start>
<end>3984</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems
%A Deriu, Jan
%A Tuggener, Don
%A von Däniken, Pius
%A Campos, Jon Ander
%A Rodrigo, Alvaro
%A Belkacem, Thiziri
%A Soroa, Aitor
%A Agirre, Eneko
%A Cieliebak, Mark
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F deriu-etal-2020-spot
%X The lack of time efficient and reliable evalu-ation methods is hampering the development of conversational dialogue systems (chat bots). Evaluations that require humans to converse with chat bots are time and cost intensive, put high cognitive demands on the human judges, and tend to yield low quality results. In this work, we introduce Spot The Bot, a cost-efficient and robust evaluation framework that replaces human-bot conversations with conversations between bots. Human judges then only annotate for each entity in a conversation whether they think it is human or not (assuming there are humans participants in these conversations). These annotations then allow us to rank chat bots regarding their ability to mimic conversational behaviour of humans. Since we expect that all bots are eventually recognized as such, we incorporate a metric that measures which chat bot is able to uphold human-like be-havior the longest, i.e.Survival Analysis. This metric has the ability to correlate a bot’s performance to certain of its characteristics (e.g.fluency or sensibleness), yielding interpretable results. The comparably low cost of our frame-work allows for frequent evaluations of chatbots during their evaluation cycle. We empirically validate our claims by applying Spot The Bot to three domains, evaluating several state-of-the-art chat bots, and drawing comparisonsto related work. The framework is released asa ready-to-use tool.
%R 10.18653/v1/2020.emnlp-main.326
%U https://aclanthology.org/2020.emnlp-main.326
%U https://doi.org/10.18653/v1/2020.emnlp-main.326
%P 3971-3984
Markdown (Informal)
[Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems](https://aclanthology.org/2020.emnlp-main.326) (Deriu et al., EMNLP 2020)
ACL
- Jan Deriu, Don Tuggener, Pius von Däniken, Jon Ander Campos, Alvaro Rodrigo, Thiziri Belkacem, Aitor Soroa, Eneko Agirre, and Mark Cieliebak. 2020. Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3971–3984, Online. Association for Computational Linguistics.