@inproceedings{ciosici-etal-2019-quantifying,
title = "Quantifying the morphosyntactic content of Brown Clusters",
author = "Ciosici, Manuel R. and
Derczynski, Leon and
Assent, Ira",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1157",
doi = "10.18653/v1/N19-1157",
pages = "1541--1550",
abstract = "Brown and Exchange word clusters have long been successfully used as word representations in Natural Language Processing (NLP) systems. Their success has been attributed to their seeming ability to represent both semantic and syntactic information. Using corpora representing several language families, we test the hypothesis that Brown and Exchange word clusters are highly effective at encoding morphosyntactic information. Our experiments show that word clusters are highly capable at distinguishing Parts of Speech. We show that increases in Average Mutual Information, the clustering algorithms{'} optimization goal, are highly correlated with improvements in encoding of morphosyntactic information. Our results provide empirical evidence that downstream NLP systems addressing tasks dependent on morphosyntactic information can benefit from word cluster features.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ciosici-etal-2019-quantifying">
<titleInfo>
<title>Quantifying the morphosyntactic content of Brown Clusters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Ciosici</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ira</namePart>
<namePart type="family">Assent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Brown and Exchange word clusters have long been successfully used as word representations in Natural Language Processing (NLP) systems. Their success has been attributed to their seeming ability to represent both semantic and syntactic information. Using corpora representing several language families, we test the hypothesis that Brown and Exchange word clusters are highly effective at encoding morphosyntactic information. Our experiments show that word clusters are highly capable at distinguishing Parts of Speech. We show that increases in Average Mutual Information, the clustering algorithms’ optimization goal, are highly correlated with improvements in encoding of morphosyntactic information. Our results provide empirical evidence that downstream NLP systems addressing tasks dependent on morphosyntactic information can benefit from word cluster features.</abstract>
<identifier type="citekey">ciosici-etal-2019-quantifying</identifier>
<identifier type="doi">10.18653/v1/N19-1157</identifier>
<location>
<url>https://aclanthology.org/N19-1157</url>
</location>
<part>
<date>2019-jun</date>
<extent unit="page">
<start>1541</start>
<end>1550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quantifying the morphosyntactic content of Brown Clusters
%A Ciosici, Manuel R.
%A Derczynski, Leon
%A Assent, Ira
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F ciosici-etal-2019-quantifying
%X Brown and Exchange word clusters have long been successfully used as word representations in Natural Language Processing (NLP) systems. Their success has been attributed to their seeming ability to represent both semantic and syntactic information. Using corpora representing several language families, we test the hypothesis that Brown and Exchange word clusters are highly effective at encoding morphosyntactic information. Our experiments show that word clusters are highly capable at distinguishing Parts of Speech. We show that increases in Average Mutual Information, the clustering algorithms’ optimization goal, are highly correlated with improvements in encoding of morphosyntactic information. Our results provide empirical evidence that downstream NLP systems addressing tasks dependent on morphosyntactic information can benefit from word cluster features.
%R 10.18653/v1/N19-1157
%U https://aclanthology.org/N19-1157
%U https://doi.org/10.18653/v1/N19-1157
%P 1541-1550
Markdown (Informal)
[Quantifying the morphosyntactic content of Brown Clusters](https://aclanthology.org/N19-1157) (Ciosici et al., NAACL 2019)
ACL
- Manuel R. Ciosici, Leon Derczynski, and Ira Assent. 2019. Quantifying the morphosyntactic content of Brown Clusters. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1541–1550, Minneapolis, Minnesota. Association for Computational Linguistics.