@inproceedings{saphra-lopez-2018-language,
title = "Language Models Learn {POS} First",
author = "Saphra, Naomi and
Lopez, Adam",
editor = "Linzen, Tal and
Chrupa{\l}a, Grzegorz and
Alishahi, Afra",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5438",
doi = "10.18653/v1/W18-5438",
pages = "328--330",
abstract = "A glut of recent research shows that language models capture linguistic structure. Such work answers the question of whether a model represents linguistic structure. But how and when are these structures acquired? Rather than treating the training process itself as a black box, we investigate how representations of linguistic structure are learned over time. In particular, we demonstrate that different aspects of linguistic structure are learned at different rates, with part of speech tagging acquired early and global topic information learned continuously.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saphra-lopez-2018-language">
<titleInfo>
<title>Language Models Learn POS First</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Lopez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</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">Afra</namePart>
<namePart type="family">Alishahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A glut of recent research shows that language models capture linguistic structure. Such work answers the question of whether a model represents linguistic structure. But how and when are these structures acquired? Rather than treating the training process itself as a black box, we investigate how representations of linguistic structure are learned over time. In particular, we demonstrate that different aspects of linguistic structure are learned at different rates, with part of speech tagging acquired early and global topic information learned continuously.</abstract>
<identifier type="citekey">saphra-lopez-2018-language</identifier>
<identifier type="doi">10.18653/v1/W18-5438</identifier>
<location>
<url>https://aclanthology.org/W18-5438</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>328</start>
<end>330</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Models Learn POS First
%A Saphra, Naomi
%A Lopez, Adam
%Y Linzen, Tal
%Y Chrupała, Grzegorz
%Y Alishahi, Afra
%S Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F saphra-lopez-2018-language
%X A glut of recent research shows that language models capture linguistic structure. Such work answers the question of whether a model represents linguistic structure. But how and when are these structures acquired? Rather than treating the training process itself as a black box, we investigate how representations of linguistic structure are learned over time. In particular, we demonstrate that different aspects of linguistic structure are learned at different rates, with part of speech tagging acquired early and global topic information learned continuously.
%R 10.18653/v1/W18-5438
%U https://aclanthology.org/W18-5438
%U https://doi.org/10.18653/v1/W18-5438
%P 328-330
Markdown (Informal)
[Language Models Learn POS First](https://aclanthology.org/W18-5438) (Saphra & Lopez, EMNLP 2018)
ACL
- Naomi Saphra and Adam Lopez. 2018. Language Models Learn POS First. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 328–330, Brussels, Belgium. Association for Computational Linguistics.