@inproceedings{zhang-etal-2020-language,
title = "Do Language Embeddings capture Scales?",
author = "Zhang, Xikun and
Ramachandran, Deepak and
Tenney, Ian and
Elazar, Yanai and
Roth, Dan",
editor = "Alishahi, Afra and
Belinkov, Yonatan and
Chrupa{\l}a, Grzegorz and
Hupkes, Dieuwke and
Pinter, Yuval and
Sajjad, Hassan",
booktitle = "Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.blackboxnlp-1.27/",
doi = "10.18653/v1/2020.blackboxnlp-1.27",
pages = "292--299",
abstract = "Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that pretrained language models capture a significant amount of this information but are short of the capability required for general common-sense reasoning. We identify contextual information in pre-training and numeracy as two key factors affecting their performance, and show that a simple method of canonicalizing numbers can have a significant effect on the results."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2020-language">
<titleInfo>
<title>Do Language Embeddings capture Scales?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xikun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Ramachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Tenney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanai</namePart>
<namePart type="family">Elazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afra</namePart>
<namePart type="family">Alishahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grzegorz</namePart>
<namePart type="family">Chrupała</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that pretrained language models capture a significant amount of this information but are short of the capability required for general common-sense reasoning. We identify contextual information in pre-training and numeracy as two key factors affecting their performance, and show that a simple method of canonicalizing numbers can have a significant effect on the results.</abstract>
<identifier type="citekey">zhang-etal-2020-language</identifier>
<identifier type="doi">10.18653/v1/2020.blackboxnlp-1.27</identifier>
<location>
<url>https://aclanthology.org/2020.blackboxnlp-1.27/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>292</start>
<end>299</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Language Embeddings capture Scales?
%A Zhang, Xikun
%A Ramachandran, Deepak
%A Tenney, Ian
%A Elazar, Yanai
%A Roth, Dan
%Y Alishahi, Afra
%Y Belinkov, Yonatan
%Y Chrupała, Grzegorz
%Y Hupkes, Dieuwke
%Y Pinter, Yuval
%Y Sajjad, Hassan
%S Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zhang-etal-2020-language
%X Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that pretrained language models capture a significant amount of this information but are short of the capability required for general common-sense reasoning. We identify contextual information in pre-training and numeracy as two key factors affecting their performance, and show that a simple method of canonicalizing numbers can have a significant effect on the results.
%R 10.18653/v1/2020.blackboxnlp-1.27
%U https://aclanthology.org/2020.blackboxnlp-1.27/
%U https://doi.org/10.18653/v1/2020.blackboxnlp-1.27
%P 292-299
Markdown (Informal)
[Do Language Embeddings capture Scales?](https://aclanthology.org/2020.blackboxnlp-1.27/) (Zhang et al., BlackboxNLP 2020)
ACL
- Xikun Zhang, Deepak Ramachandran, Ian Tenney, Yanai Elazar, and Dan Roth. 2020. Do Language Embeddings capture Scales?. In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 292–299, Online. Association for Computational Linguistics.