@inproceedings{anthonio-etal-2022-clarifying,
title = "Clarifying Implicit and Underspecified Phrases in Instructional Text",
author = "Anthonio, Talita and
Sauer, Anna and
Roth, Michael",
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-1.354",
pages = "3319--3330",
abstract = "Natural language inherently consists of implicit and underspecified phrases, which represent potential sources of misunderstanding. In this paper, we present a data set of such phrases in English from instructional texts together with multiple possible clarifications. Our data set, henceforth called CLAIRE, is based on a corpus of revision histories from wikiHow, from which we extract human clarifications that resolve an implicit or underspecified phrase. We show how language modeling can be used to generate alternate clarifications, which may or may not be compatible with the human clarification. Based on plausibility judgements for each clarification, we define the task of distinguishing between plausible and implausible clarifications. We provide several baseline models for this task and analyze to what extent different clarifications represent multiple readings as a first step to investigate misunderstandings caused by implicit/underspecified language in instructional texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anthonio-etal-2022-clarifying">
<titleInfo>
<title>Clarifying Implicit and Underspecified Phrases in Instructional Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Talita</namePart>
<namePart type="family">Anthonio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Sauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Roth</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>Natural language inherently consists of implicit and underspecified phrases, which represent potential sources of misunderstanding. In this paper, we present a data set of such phrases in English from instructional texts together with multiple possible clarifications. Our data set, henceforth called CLAIRE, is based on a corpus of revision histories from wikiHow, from which we extract human clarifications that resolve an implicit or underspecified phrase. We show how language modeling can be used to generate alternate clarifications, which may or may not be compatible with the human clarification. Based on plausibility judgements for each clarification, we define the task of distinguishing between plausible and implausible clarifications. We provide several baseline models for this task and analyze to what extent different clarifications represent multiple readings as a first step to investigate misunderstandings caused by implicit/underspecified language in instructional texts.</abstract>
<identifier type="citekey">anthonio-etal-2022-clarifying</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.354</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3319</start>
<end>3330</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clarifying Implicit and Underspecified Phrases in Instructional Text
%A Anthonio, Talita
%A Sauer, Anna
%A Roth, Michael
%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 anthonio-etal-2022-clarifying
%X Natural language inherently consists of implicit and underspecified phrases, which represent potential sources of misunderstanding. In this paper, we present a data set of such phrases in English from instructional texts together with multiple possible clarifications. Our data set, henceforth called CLAIRE, is based on a corpus of revision histories from wikiHow, from which we extract human clarifications that resolve an implicit or underspecified phrase. We show how language modeling can be used to generate alternate clarifications, which may or may not be compatible with the human clarification. Based on plausibility judgements for each clarification, we define the task of distinguishing between plausible and implausible clarifications. We provide several baseline models for this task and analyze to what extent different clarifications represent multiple readings as a first step to investigate misunderstandings caused by implicit/underspecified language in instructional texts.
%U https://aclanthology.org/2022.lrec-1.354
%P 3319-3330
Markdown (Informal)
[Clarifying Implicit and Underspecified Phrases in Instructional Text](https://aclanthology.org/2022.lrec-1.354) (Anthonio et al., LREC 2022)
ACL