@inproceedings{chierici-habash-2021-view,
title = "A View From the Crowd: Evaluation Challenges for Time-Offset Interaction Applications",
author = "Chierici, Alberto and
Habash, Nizar",
editor = "Belz, Anya and
Agarwal, Shubham and
Graham, Yvette and
Reiter, Ehud and
Shimorina, Anastasia",
booktitle = "Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.humeval-1.9",
pages = "75--85",
abstract = "Dialogue systems like chatbots, and tasks like question-answering (QA) have gained traction in recent years; yet evaluating such systems remains difficult. Reasons include the great variety in contexts and use cases for these systems as well as the high cost of human evaluation. In this paper, we focus on a specific type of dialogue systems: Time-Offset Interaction Applications (TOIAs) are intelligent, conversational software that simulates face-to-face conversations between humans and pre-recorded human avatars. Under the constraint that a TOIA is a single output system interacting with users with different expectations, we identify two challenges: first, how do we define a {`}good{'} answer? and second, what{'}s an appropriate metric to use? We explore both challenges through the creation of a novel dataset that identifies multiple good answers to specific TOIA questions through the help of Amazon Mechanical Turk workers. This {`}view from the crowd{'} allows us to study the variations of how TOIA interrogators perceive its answers. Our contributions include the annotated dataset that we make publicly available and the proposal of Success Rate @k as an evaluation metric that is more appropriate than the traditional QA{'}s and information retrieval{'}s metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chierici-habash-2021-view">
<titleInfo>
<title>A View From the Crowd: Evaluation Challenges for Time-Offset Interaction Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Chierici</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</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>Dialogue systems like chatbots, and tasks like question-answering (QA) have gained traction in recent years; yet evaluating such systems remains difficult. Reasons include the great variety in contexts and use cases for these systems as well as the high cost of human evaluation. In this paper, we focus on a specific type of dialogue systems: Time-Offset Interaction Applications (TOIAs) are intelligent, conversational software that simulates face-to-face conversations between humans and pre-recorded human avatars. Under the constraint that a TOIA is a single output system interacting with users with different expectations, we identify two challenges: first, how do we define a ‘good’ answer? and second, what’s an appropriate metric to use? We explore both challenges through the creation of a novel dataset that identifies multiple good answers to specific TOIA questions through the help of Amazon Mechanical Turk workers. This ‘view from the crowd’ allows us to study the variations of how TOIA interrogators perceive its answers. Our contributions include the annotated dataset that we make publicly available and the proposal of Success Rate @k as an evaluation metric that is more appropriate than the traditional QA’s and information retrieval’s metrics.</abstract>
<identifier type="citekey">chierici-habash-2021-view</identifier>
<location>
<url>https://aclanthology.org/2021.humeval-1.9</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>75</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A View From the Crowd: Evaluation Challenges for Time-Offset Interaction Applications
%A Chierici, Alberto
%A Habash, Nizar
%Y Belz, Anya
%Y Agarwal, Shubham
%Y Graham, Yvette
%Y Reiter, Ehud
%Y Shimorina, Anastasia
%S Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F chierici-habash-2021-view
%X Dialogue systems like chatbots, and tasks like question-answering (QA) have gained traction in recent years; yet evaluating such systems remains difficult. Reasons include the great variety in contexts and use cases for these systems as well as the high cost of human evaluation. In this paper, we focus on a specific type of dialogue systems: Time-Offset Interaction Applications (TOIAs) are intelligent, conversational software that simulates face-to-face conversations between humans and pre-recorded human avatars. Under the constraint that a TOIA is a single output system interacting with users with different expectations, we identify two challenges: first, how do we define a ‘good’ answer? and second, what’s an appropriate metric to use? We explore both challenges through the creation of a novel dataset that identifies multiple good answers to specific TOIA questions through the help of Amazon Mechanical Turk workers. This ‘view from the crowd’ allows us to study the variations of how TOIA interrogators perceive its answers. Our contributions include the annotated dataset that we make publicly available and the proposal of Success Rate @k as an evaluation metric that is more appropriate than the traditional QA’s and information retrieval’s metrics.
%U https://aclanthology.org/2021.humeval-1.9
%P 75-85
Markdown (Informal)
[A View From the Crowd: Evaluation Challenges for Time-Offset Interaction Applications](https://aclanthology.org/2021.humeval-1.9) (Chierici & Habash, HumEval 2021)
ACL