@inproceedings{lauriola-etal-2022-building,
title = "Building a Dataset for Automatically Learning to Detect Questions Requiring Clarification",
author = "Lauriola, Ivano and
Small, Kevin and
Moschitti, Alessandro",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.502",
pages = "4701--4707",
abstract = "Question Answering (QA) systems aim to return correct and concise answers in response to user questions. QA research generally assumes all questions are intelligible and unambiguous, which is unrealistic in practice as questions frequently encountered by virtual assistants are ambiguous or noisy. In this work, we propose to make QA systems more robust via the following two-step process: (1) classify if the input question is intelligible and (2) for such questions with contextual ambiguity, return a clarification question. We describe a new open-domain clarification corpus containing user questions sampled from Quora, which is useful for building machine learning approaches to solving these tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lauriola-etal-2022-building">
<titleInfo>
<title>Building a Dataset for Automatically Learning to Detect Questions Requiring Clarification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivano</namePart>
<namePart type="family">Lauriola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Small</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Question Answering (QA) systems aim to return correct and concise answers in response to user questions. QA research generally assumes all questions are intelligible and unambiguous, which is unrealistic in practice as questions frequently encountered by virtual assistants are ambiguous or noisy. In this work, we propose to make QA systems more robust via the following two-step process: (1) classify if the input question is intelligible and (2) for such questions with contextual ambiguity, return a clarification question. We describe a new open-domain clarification corpus containing user questions sampled from Quora, which is useful for building machine learning approaches to solving these tasks.</abstract>
<identifier type="citekey">lauriola-etal-2022-building</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.502</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4701</start>
<end>4707</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Dataset for Automatically Learning to Detect Questions Requiring Clarification
%A Lauriola, Ivano
%A Small, Kevin
%A Moschitti, Alessandro
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F lauriola-etal-2022-building
%X Question Answering (QA) systems aim to return correct and concise answers in response to user questions. QA research generally assumes all questions are intelligible and unambiguous, which is unrealistic in practice as questions frequently encountered by virtual assistants are ambiguous or noisy. In this work, we propose to make QA systems more robust via the following two-step process: (1) classify if the input question is intelligible and (2) for such questions with contextual ambiguity, return a clarification question. We describe a new open-domain clarification corpus containing user questions sampled from Quora, which is useful for building machine learning approaches to solving these tasks.
%U https://aclanthology.org/2022.lrec-1.502
%P 4701-4707
Markdown (Informal)
[Building a Dataset for Automatically Learning to Detect Questions Requiring Clarification](https://aclanthology.org/2022.lrec-1.502) (Lauriola et al., LREC 2022)
ACL