@inproceedings{thawani-etal-2021-representing,
title = "Representing Numbers in {NLP}: a Survey and a Vision",
author = "Thawani, Avijit and
Pujara, Jay and
Ilievski, Filip and
Szekely, Pedro",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.53",
doi = "10.18653/v1/2021.naacl-main.53",
pages = "644--656",
abstract = "NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP work on numeracy into a comprehensive taxonomy of tasks and methods. We break down the subjective notion of numeracy into 7 subtasks, arranged along two dimensions: granularity (exact vs approximate) and units (abstract vs grounded). We analyze the myriad representational choices made by over a dozen previously published number encoders and decoders. We synthesize best practices for representing numbers in text and articulate a vision for holistic numeracy in NLP, comprised of design trade-offs and a unified evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thawani-etal-2021-representing">
<titleInfo>
<title>Representing Numbers in NLP: a Survey and a Vision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avijit</namePart>
<namePart type="family">Thawani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Pujara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Ilievski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Szekely</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP work on numeracy into a comprehensive taxonomy of tasks and methods. We break down the subjective notion of numeracy into 7 subtasks, arranged along two dimensions: granularity (exact vs approximate) and units (abstract vs grounded). We analyze the myriad representational choices made by over a dozen previously published number encoders and decoders. We synthesize best practices for representing numbers in text and articulate a vision for holistic numeracy in NLP, comprised of design trade-offs and a unified evaluation.</abstract>
<identifier type="citekey">thawani-etal-2021-representing</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.53</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.53</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>644</start>
<end>656</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Representing Numbers in NLP: a Survey and a Vision
%A Thawani, Avijit
%A Pujara, Jay
%A Ilievski, Filip
%A Szekely, Pedro
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F thawani-etal-2021-representing
%X NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP work on numeracy into a comprehensive taxonomy of tasks and methods. We break down the subjective notion of numeracy into 7 subtasks, arranged along two dimensions: granularity (exact vs approximate) and units (abstract vs grounded). We analyze the myriad representational choices made by over a dozen previously published number encoders and decoders. We synthesize best practices for representing numbers in text and articulate a vision for holistic numeracy in NLP, comprised of design trade-offs and a unified evaluation.
%R 10.18653/v1/2021.naacl-main.53
%U https://aclanthology.org/2021.naacl-main.53
%U https://doi.org/10.18653/v1/2021.naacl-main.53
%P 644-656
Markdown (Informal)
[Representing Numbers in NLP: a Survey and a Vision](https://aclanthology.org/2021.naacl-main.53) (Thawani et al., NAACL 2021)
ACL
- Avijit Thawani, Jay Pujara, Filip Ilievski, and Pedro Szekely. 2021. Representing Numbers in NLP: a Survey and a Vision. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 644–656, Online. Association for Computational Linguistics.