@inproceedings{spokoyny-etal-2022-numerical,
title = "Numerical Correlation in Text",
author = "Spokoyny, Daniel and
Wu, Chien-Sheng and
Xiong, Caiming",
editor = "Ferreira, Deborah and
Valentino, Marco and
Freitas, Andre and
Welleck, Sean and
Schubotz, Moritz",
booktitle = "Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.mathnlp-1.5",
doi = "10.18653/v1/2022.mathnlp-1.5",
pages = "33--39",
abstract = "Evaluation of quantitative reasoning of large language models is an important step towards understanding their current capabilities and limitations. We propose a new task, Numerical Correlation in Text, which requires models to identify the correlation between two numbers in a sentence. To this end, we introduce a new dataset, which contains over 2,000 Wikipedia sentences with two numbers and their correlation labels. Using this dataset we are able to show that recent numerically aware pretraining methods for language models do not help generalization on this task posing a challenge for future work in this area.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spokoyny-etal-2022-numerical">
<titleInfo>
<title>Numerical Correlation in Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Spokoyny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chien-Sheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deborah</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">Welleck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moritz</namePart>
<namePart type="family">Schubotz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Evaluation of quantitative reasoning of large language models is an important step towards understanding their current capabilities and limitations. We propose a new task, Numerical Correlation in Text, which requires models to identify the correlation between two numbers in a sentence. To this end, we introduce a new dataset, which contains over 2,000 Wikipedia sentences with two numbers and their correlation labels. Using this dataset we are able to show that recent numerically aware pretraining methods for language models do not help generalization on this task posing a challenge for future work in this area.</abstract>
<identifier type="citekey">spokoyny-etal-2022-numerical</identifier>
<identifier type="doi">10.18653/v1/2022.mathnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2022.mathnlp-1.5</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>33</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Numerical Correlation in Text
%A Spokoyny, Daniel
%A Wu, Chien-Sheng
%A Xiong, Caiming
%Y Ferreira, Deborah
%Y Valentino, Marco
%Y Freitas, Andre
%Y Welleck, Sean
%Y Schubotz, Moritz
%S Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F spokoyny-etal-2022-numerical
%X Evaluation of quantitative reasoning of large language models is an important step towards understanding their current capabilities and limitations. We propose a new task, Numerical Correlation in Text, which requires models to identify the correlation between two numbers in a sentence. To this end, we introduce a new dataset, which contains over 2,000 Wikipedia sentences with two numbers and their correlation labels. Using this dataset we are able to show that recent numerically aware pretraining methods for language models do not help generalization on this task posing a challenge for future work in this area.
%R 10.18653/v1/2022.mathnlp-1.5
%U https://aclanthology.org/2022.mathnlp-1.5
%U https://doi.org/10.18653/v1/2022.mathnlp-1.5
%P 33-39
Markdown (Informal)
[Numerical Correlation in Text](https://aclanthology.org/2022.mathnlp-1.5) (Spokoyny et al., MathNLP 2022)
ACL
- Daniel Spokoyny, Chien-Sheng Wu, and Caiming Xiong. 2022. Numerical Correlation in Text. In Proceedings of the 1st Workshop on Mathematical Natural Language Processing (MathNLP), pages 33–39, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.