@inproceedings{rodriguez-etal-2022-clustering,
title = "Clustering Examples in Multi-Dataset Benchmarks with Item Response Theory",
author = "Rodriguez, Pedro and
Htut, Phu Mon and
Lalor, John and
Sedoc, Jo{\~a}o",
editor = "Tafreshi, Shabnam and
Sedoc, Jo{\~a}o and
Rogers, Anna and
Drozd, Aleksandr and
Rumshisky, Anna and
Akula, Arjun",
booktitle = "Proceedings of the Third Workshop on Insights from Negative Results in NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.insights-1.14",
doi = "10.18653/v1/2022.insights-1.14",
pages = "100--112",
abstract = "In natural language processing, multi-dataset benchmarks for common tasks (e.g., SuperGLUE for natural language inference and MRQA for question answering) have risen in importance. Invariably, tasks and individual examples vary in difficulty. Recent analysis methods infer properties of examples such as difficulty. In particular, Item Response Theory (IRT) jointly infers example and model properties from the output of benchmark tasks (i.e., scores for each model-example pair). Therefore, it seems sensible that methods like IRT should be able to detect differences between datasets in a task. This work shows that current IRT models are not as good at identifying differences as we would expect, explain why this is difficult, and outline future directions that incorporate more (textual) signal from examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-etal-2022-clustering">
<titleInfo>
<title>Clustering Examples in Multi-Dataset Benchmarks with Item Response Theory</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phu</namePart>
<namePart type="given">Mon</namePart>
<namePart type="family">Htut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Lalor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In natural language processing, multi-dataset benchmarks for common tasks (e.g., SuperGLUE for natural language inference and MRQA for question answering) have risen in importance. Invariably, tasks and individual examples vary in difficulty. Recent analysis methods infer properties of examples such as difficulty. In particular, Item Response Theory (IRT) jointly infers example and model properties from the output of benchmark tasks (i.e., scores for each model-example pair). Therefore, it seems sensible that methods like IRT should be able to detect differences between datasets in a task. This work shows that current IRT models are not as good at identifying differences as we would expect, explain why this is difficult, and outline future directions that incorporate more (textual) signal from examples.</abstract>
<identifier type="citekey">rodriguez-etal-2022-clustering</identifier>
<identifier type="doi">10.18653/v1/2022.insights-1.14</identifier>
<location>
<url>https://aclanthology.org/2022.insights-1.14</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>100</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clustering Examples in Multi-Dataset Benchmarks with Item Response Theory
%A Rodriguez, Pedro
%A Htut, Phu Mon
%A Lalor, John
%A Sedoc, João
%Y Tafreshi, Shabnam
%Y Sedoc, João
%Y Rogers, Anna
%Y Drozd, Aleksandr
%Y Rumshisky, Anna
%Y Akula, Arjun
%S Proceedings of the Third Workshop on Insights from Negative Results in NLP
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F rodriguez-etal-2022-clustering
%X In natural language processing, multi-dataset benchmarks for common tasks (e.g., SuperGLUE for natural language inference and MRQA for question answering) have risen in importance. Invariably, tasks and individual examples vary in difficulty. Recent analysis methods infer properties of examples such as difficulty. In particular, Item Response Theory (IRT) jointly infers example and model properties from the output of benchmark tasks (i.e., scores for each model-example pair). Therefore, it seems sensible that methods like IRT should be able to detect differences between datasets in a task. This work shows that current IRT models are not as good at identifying differences as we would expect, explain why this is difficult, and outline future directions that incorporate more (textual) signal from examples.
%R 10.18653/v1/2022.insights-1.14
%U https://aclanthology.org/2022.insights-1.14
%U https://doi.org/10.18653/v1/2022.insights-1.14
%P 100-112
Markdown (Informal)
[Clustering Examples in Multi-Dataset Benchmarks with Item Response Theory](https://aclanthology.org/2022.insights-1.14) (Rodriguez et al., insights 2022)
ACL