@inproceedings{sileo-etal-2022-pragmatics,
title = "A Pragmatics-Centered Evaluation Framework for Natural Language Understanding",
author = "Sileo, Damien and
Muller, Philippe and
Van de Cruys, Tim and
Pradel, Camille",
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-1.255/",
pages = "2382--2394",
abstract = "New models for natural language understanding have recently made an unparalleled amount of progress, which has led some researchers to suggest that the models induce universal text representations. However, current benchmarks are predominantly targeting semantic phenomena; we make the case that pragmatics needs to take center stage in the evaluation of natural language understanding. We introduce PragmEval, a new benchmark for the evaluation of natural language understanding, that unites 11 pragmatics-focused evaluation datasets for English. PragmEval can be used as supplementary training data in a multi-task learning setup, and is publicly available, alongside the code for gathering and preprocessing the datasets. Using our evaluation suite, we show that natural language inference, a widely used pretraining task, does not result in genuinely universal representations, which presents a new challenge for multi-task learning."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sileo-etal-2022-pragmatics">
<titleInfo>
<title>A Pragmatics-Centered Evaluation Framework for Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Sileo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Van de Cruys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Pradel</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>New models for natural language understanding have recently made an unparalleled amount of progress, which has led some researchers to suggest that the models induce universal text representations. However, current benchmarks are predominantly targeting semantic phenomena; we make the case that pragmatics needs to take center stage in the evaluation of natural language understanding. We introduce PragmEval, a new benchmark for the evaluation of natural language understanding, that unites 11 pragmatics-focused evaluation datasets for English. PragmEval can be used as supplementary training data in a multi-task learning setup, and is publicly available, alongside the code for gathering and preprocessing the datasets. Using our evaluation suite, we show that natural language inference, a widely used pretraining task, does not result in genuinely universal representations, which presents a new challenge for multi-task learning.</abstract>
<identifier type="citekey">sileo-etal-2022-pragmatics</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.255/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2382</start>
<end>2394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Pragmatics-Centered Evaluation Framework for Natural Language Understanding
%A Sileo, Damien
%A Muller, Philippe
%A Van de Cruys, Tim
%A Pradel, Camille
%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 sileo-etal-2022-pragmatics
%X New models for natural language understanding have recently made an unparalleled amount of progress, which has led some researchers to suggest that the models induce universal text representations. However, current benchmarks are predominantly targeting semantic phenomena; we make the case that pragmatics needs to take center stage in the evaluation of natural language understanding. We introduce PragmEval, a new benchmark for the evaluation of natural language understanding, that unites 11 pragmatics-focused evaluation datasets for English. PragmEval can be used as supplementary training data in a multi-task learning setup, and is publicly available, alongside the code for gathering and preprocessing the datasets. Using our evaluation suite, we show that natural language inference, a widely used pretraining task, does not result in genuinely universal representations, which presents a new challenge for multi-task learning.
%U https://aclanthology.org/2022.lrec-1.255/
%P 2382-2394
Markdown (Informal)
[A Pragmatics-Centered Evaluation Framework for Natural Language Understanding](https://aclanthology.org/2022.lrec-1.255/) (Sileo et al., LREC 2022)
ACL