@inproceedings{haley-2020-bert,
title = "This is a {BERT}. Now there are several of them. Can they generalize to novel words?",
author = "Haley, Coleman",
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-1.31",
doi = "10.18653/v1/2020.blackboxnlp-1.31",
pages = "333--341",
abstract = "Recently, large-scale pre-trained neural network models such as BERT have achieved many state-of-the-art results in natural language processing. Recent work has explored the linguistic capacities of these models. However, no work has focused on the ability of these models to generalize these capacities to novel words. This type of generalization is exhibited by humans, and is intimately related to morphology{---}humans are in many cases able to identify inflections of novel words in the appropriate context. This type of morphological capacity has not been previously tested in BERT models, and is important for morphologically-rich languages, which are under-studied in the literature regarding BERT{'}s linguistic capacities. In this work, we investigate this by considering monolingual and multilingual BERT models{'} abilities to agree in number with novel plural words in English, French, German, Spanish, and Dutch. We find that many models are not able to reliably determine plurality of novel words, suggesting potential deficiencies in the morphological capacities of BERT models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haley-2020-bert">
<titleInfo>
<title>This is a BERT. Now there are several of them. Can they generalize to novel words?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Coleman</namePart>
<namePart type="family">Haley</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>Recently, large-scale pre-trained neural network models such as BERT have achieved many state-of-the-art results in natural language processing. Recent work has explored the linguistic capacities of these models. However, no work has focused on the ability of these models to generalize these capacities to novel words. This type of generalization is exhibited by humans, and is intimately related to morphology—humans are in many cases able to identify inflections of novel words in the appropriate context. This type of morphological capacity has not been previously tested in BERT models, and is important for morphologically-rich languages, which are under-studied in the literature regarding BERT’s linguistic capacities. In this work, we investigate this by considering monolingual and multilingual BERT models’ abilities to agree in number with novel plural words in English, French, German, Spanish, and Dutch. We find that many models are not able to reliably determine plurality of novel words, suggesting potential deficiencies in the morphological capacities of BERT models.</abstract>
<identifier type="citekey">haley-2020-bert</identifier>
<identifier type="doi">10.18653/v1/2020.blackboxnlp-1.31</identifier>
<location>
<url>https://aclanthology.org/2020.blackboxnlp-1.31</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>333</start>
<end>341</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T This is a BERT. Now there are several of them. Can they generalize to novel words?
%A Haley, Coleman
%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 haley-2020-bert
%X Recently, large-scale pre-trained neural network models such as BERT have achieved many state-of-the-art results in natural language processing. Recent work has explored the linguistic capacities of these models. However, no work has focused on the ability of these models to generalize these capacities to novel words. This type of generalization is exhibited by humans, and is intimately related to morphology—humans are in many cases able to identify inflections of novel words in the appropriate context. This type of morphological capacity has not been previously tested in BERT models, and is important for morphologically-rich languages, which are under-studied in the literature regarding BERT’s linguistic capacities. In this work, we investigate this by considering monolingual and multilingual BERT models’ abilities to agree in number with novel plural words in English, French, German, Spanish, and Dutch. We find that many models are not able to reliably determine plurality of novel words, suggesting potential deficiencies in the morphological capacities of BERT models.
%R 10.18653/v1/2020.blackboxnlp-1.31
%U https://aclanthology.org/2020.blackboxnlp-1.31
%U https://doi.org/10.18653/v1/2020.blackboxnlp-1.31
%P 333-341
Markdown (Informal)
[This is a BERT. Now there are several of them. Can they generalize to novel words?](https://aclanthology.org/2020.blackboxnlp-1.31) (Haley, BlackboxNLP 2020)
ACL