@inproceedings{verwimp-etal-2017-character,
title = "Character-Word {LSTM} Language Models",
author = "Verwimp, Lyan and
Pelemans, Joris and
Van hamme, Hugo and
Wambacq, Patrick",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-1040",
pages = "417--427",
abstract = "We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal structural (dis)similarities between words and can even be used when a word is out-of-vocabulary, thus improving the modeling of infrequent and unknown words. By concatenating word and character embeddings, we achieve up to 2.77{\%} relative improvement on English compared to a baseline model with a similar amount of parameters and 4.57{\%} on Dutch. Moreover, we also outperform baseline word-level models with a larger number of parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verwimp-etal-2017-character">
<titleInfo>
<title>Character-Word LSTM Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lyan</namePart>
<namePart type="family">Verwimp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joris</namePart>
<namePart type="family">Pelemans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Van hamme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Wambacq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal structural (dis)similarities between words and can even be used when a word is out-of-vocabulary, thus improving the modeling of infrequent and unknown words. By concatenating word and character embeddings, we achieve up to 2.77% relative improvement on English compared to a baseline model with a similar amount of parameters and 4.57% on Dutch. Moreover, we also outperform baseline word-level models with a larger number of parameters.</abstract>
<identifier type="citekey">verwimp-etal-2017-character</identifier>
<location>
<url>https://aclanthology.org/E17-1040</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>417</start>
<end>427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Character-Word LSTM Language Models
%A Verwimp, Lyan
%A Pelemans, Joris
%A Van hamme, Hugo
%A Wambacq, Patrick
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F verwimp-etal-2017-character
%X We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal structural (dis)similarities between words and can even be used when a word is out-of-vocabulary, thus improving the modeling of infrequent and unknown words. By concatenating word and character embeddings, we achieve up to 2.77% relative improvement on English compared to a baseline model with a similar amount of parameters and 4.57% on Dutch. Moreover, we also outperform baseline word-level models with a larger number of parameters.
%U https://aclanthology.org/E17-1040
%P 417-427
Markdown (Informal)
[Character-Word LSTM Language Models](https://aclanthology.org/E17-1040) (Verwimp et al., EACL 2017)
ACL
- Lyan Verwimp, Joris Pelemans, Hugo Van hamme, and Patrick Wambacq. 2017. Character-Word LSTM Language Models. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 417–427, Valencia, Spain. Association for Computational Linguistics.