@inproceedings{berend-2020-sparsity,
title = "Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations",
author = "Berend, G{\'a}bor",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.683",
doi = "10.18653/v1/2020.emnlp-main.683",
pages = "8498--8508",
abstract = "In this paper, we demonstrate that by utilizing sparse word representations, it becomes possible to surpass the results of more complex task-specific models on the task of fine-grained all-words word sense disambiguation. Our proposed algorithm relies on an overcomplete set of semantic basis vectors that allows us to obtain sparse contextualized word representations. We introduce such an information theory-inspired synset representation based on the co-occurrence of word senses and non-zero coordinates for word forms which allows us to achieve an aggregated F-score of 78.8 over a combination of five standard word sense disambiguating benchmark datasets. We also demonstrate the general applicability of our proposed framework by evaluating it towards part-of-speech tagging on four different treebanks. Our results indicate a significant improvement over the application of the dense word representations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berend-2020-sparsity">
<titleInfo>
<title>Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gábor</namePart>
<namePart type="family">Berend</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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>In this paper, we demonstrate that by utilizing sparse word representations, it becomes possible to surpass the results of more complex task-specific models on the task of fine-grained all-words word sense disambiguation. Our proposed algorithm relies on an overcomplete set of semantic basis vectors that allows us to obtain sparse contextualized word representations. We introduce such an information theory-inspired synset representation based on the co-occurrence of word senses and non-zero coordinates for word forms which allows us to achieve an aggregated F-score of 78.8 over a combination of five standard word sense disambiguating benchmark datasets. We also demonstrate the general applicability of our proposed framework by evaluating it towards part-of-speech tagging on four different treebanks. Our results indicate a significant improvement over the application of the dense word representations.</abstract>
<identifier type="citekey">berend-2020-sparsity</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.683</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.683</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>8498</start>
<end>8508</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations
%A Berend, Gábor
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F berend-2020-sparsity
%X In this paper, we demonstrate that by utilizing sparse word representations, it becomes possible to surpass the results of more complex task-specific models on the task of fine-grained all-words word sense disambiguation. Our proposed algorithm relies on an overcomplete set of semantic basis vectors that allows us to obtain sparse contextualized word representations. We introduce such an information theory-inspired synset representation based on the co-occurrence of word senses and non-zero coordinates for word forms which allows us to achieve an aggregated F-score of 78.8 over a combination of five standard word sense disambiguating benchmark datasets. We also demonstrate the general applicability of our proposed framework by evaluating it towards part-of-speech tagging on four different treebanks. Our results indicate a significant improvement over the application of the dense word representations.
%R 10.18653/v1/2020.emnlp-main.683
%U https://aclanthology.org/2020.emnlp-main.683
%U https://doi.org/10.18653/v1/2020.emnlp-main.683
%P 8498-8508
Markdown (Informal)
[Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations](https://aclanthology.org/2020.emnlp-main.683) (Berend, EMNLP 2020)
ACL