@inproceedings{grzegorczyk-kurdziel-2018-disambiguated,
title = "Disambiguated skip-gram model",
author = "Grzegorczyk, Karol and
Kurdziel, Marcin",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1174/",
doi = "10.18653/v1/D18-1174",
pages = "1445--1454",
abstract = "We present disambiguated skip-gram: a neural-probabilistic model for learning multi-sense distributed representations of words. Disambiguated skip-gram jointly estimates a skip-gram-like context word prediction model and a word sense disambiguation model. Unlike previous probabilistic models for learning multi-sense word embeddings, disambiguated skip-gram is end-to-end differentiable and can be interpreted as a simple feed-forward neural network. We also introduce an effective pruning strategy for the embeddings learned by disambiguated skip-gram. This allows us to control the granularity of representations learned by our model. In experimental evaluation disambiguated skip-gram improves state-of-the are results in several word sense induction benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grzegorczyk-kurdziel-2018-disambiguated">
<titleInfo>
<title>Disambiguated skip-gram model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karol</namePart>
<namePart type="family">Grzegorczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Kurdziel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</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>We present disambiguated skip-gram: a neural-probabilistic model for learning multi-sense distributed representations of words. Disambiguated skip-gram jointly estimates a skip-gram-like context word prediction model and a word sense disambiguation model. Unlike previous probabilistic models for learning multi-sense word embeddings, disambiguated skip-gram is end-to-end differentiable and can be interpreted as a simple feed-forward neural network. We also introduce an effective pruning strategy for the embeddings learned by disambiguated skip-gram. This allows us to control the granularity of representations learned by our model. In experimental evaluation disambiguated skip-gram improves state-of-the are results in several word sense induction benchmarks.</abstract>
<identifier type="citekey">grzegorczyk-kurdziel-2018-disambiguated</identifier>
<identifier type="doi">10.18653/v1/D18-1174</identifier>
<location>
<url>https://aclanthology.org/D18-1174/</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>1445</start>
<end>1454</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disambiguated skip-gram model
%A Grzegorczyk, Karol
%A Kurdziel, Marcin
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F grzegorczyk-kurdziel-2018-disambiguated
%X We present disambiguated skip-gram: a neural-probabilistic model for learning multi-sense distributed representations of words. Disambiguated skip-gram jointly estimates a skip-gram-like context word prediction model and a word sense disambiguation model. Unlike previous probabilistic models for learning multi-sense word embeddings, disambiguated skip-gram is end-to-end differentiable and can be interpreted as a simple feed-forward neural network. We also introduce an effective pruning strategy for the embeddings learned by disambiguated skip-gram. This allows us to control the granularity of representations learned by our model. In experimental evaluation disambiguated skip-gram improves state-of-the are results in several word sense induction benchmarks.
%R 10.18653/v1/D18-1174
%U https://aclanthology.org/D18-1174/
%U https://doi.org/10.18653/v1/D18-1174
%P 1445-1454
Markdown (Informal)
[Disambiguated skip-gram model](https://aclanthology.org/D18-1174/) (Grzegorczyk & Kurdziel, EMNLP 2018)
ACL
- Karol Grzegorczyk and Marcin Kurdziel. 2018. Disambiguated skip-gram model. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1445–1454, Brussels, Belgium. Association for Computational Linguistics.