@inproceedings{zhao-etal-2018-generalizing,
title = "Generalizing Word Embeddings using Bag of Subwords",
author = "Zhao, Jinman and
Mudgal, Sidharth and
Liang, Yingyu",
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/D18-1059",
doi = "10.18653/v1/D18-1059",
pages = "601--606",
abstract = "We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character $n$-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model{'}s ability in capturing the relationship between words{'} textual representations and their embeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2018-generalizing">
<titleInfo>
<title>Generalizing Word Embeddings using Bag of Subwords</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinman</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sidharth</namePart>
<namePart type="family">Mudgal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingyu</namePart>
<namePart type="family">Liang</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 approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character n-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model’s ability in capturing the relationship between words’ textual representations and their embeddings.</abstract>
<identifier type="citekey">zhao-etal-2018-generalizing</identifier>
<identifier type="doi">10.18653/v1/D18-1059</identifier>
<location>
<url>https://aclanthology.org/D18-1059</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>601</start>
<end>606</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalizing Word Embeddings using Bag of Subwords
%A Zhao, Jinman
%A Mudgal, Sidharth
%A Liang, Yingyu
%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 zhao-etal-2018-generalizing
%X We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character n-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model’s ability in capturing the relationship between words’ textual representations and their embeddings.
%R 10.18653/v1/D18-1059
%U https://aclanthology.org/D18-1059
%U https://doi.org/10.18653/v1/D18-1059
%P 601-606
Markdown (Informal)
[Generalizing Word Embeddings using Bag of Subwords](https://aclanthology.org/D18-1059) (Zhao et al., EMNLP 2018)
ACL
- Jinman Zhao, Sidharth Mudgal, and Yingyu Liang. 2018. Generalizing Word Embeddings using Bag of Subwords. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 601–606, Brussels, Belgium. Association for Computational Linguistics.