@inproceedings{erdmann-etal-2018-addressing,
title = "Addressing Noise in Multidialectal Word Embeddings",
author = "Erdmann, Alexander and
Zalmout, Nasser and
Habash, Nizar",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-2089",
doi = "10.18653/v1/P18-2089",
pages = "558--565",
abstract = "Word embeddings are crucial to many natural language processing tasks. The quality of embeddings relies on large non-noisy corpora. Arabic dialects lack large corpora and are noisy, being linguistically disparate with no standardized spelling. We make three contributions to address this noise. First, we describe simple but effective adaptations to word embedding tools to maximize the informative content leveraged in each training sentence. Second, we analyze methods for representing disparate dialects in one embedding space, either by mapping individual dialects into a shared space or learning a joint model of all dialects. Finally, we evaluate via dictionary induction, showing that two metrics not typically reported in the task enable us to analyze our contributions{'} effects on low and high frequency words. In addition to boosting performance between 2-53{\%}, we specifically improve on noisy, low frequency forms without compromising accuracy on high frequency forms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="erdmann-etal-2018-addressing">
<titleInfo>
<title>Addressing Noise in Multidialectal Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Erdmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nasser</namePart>
<namePart type="family">Zalmout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word embeddings are crucial to many natural language processing tasks. The quality of embeddings relies on large non-noisy corpora. Arabic dialects lack large corpora and are noisy, being linguistically disparate with no standardized spelling. We make three contributions to address this noise. First, we describe simple but effective adaptations to word embedding tools to maximize the informative content leveraged in each training sentence. Second, we analyze methods for representing disparate dialects in one embedding space, either by mapping individual dialects into a shared space or learning a joint model of all dialects. Finally, we evaluate via dictionary induction, showing that two metrics not typically reported in the task enable us to analyze our contributions’ effects on low and high frequency words. In addition to boosting performance between 2-53%, we specifically improve on noisy, low frequency forms without compromising accuracy on high frequency forms.</abstract>
<identifier type="citekey">erdmann-etal-2018-addressing</identifier>
<identifier type="doi">10.18653/v1/P18-2089</identifier>
<location>
<url>https://aclanthology.org/P18-2089</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>558</start>
<end>565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Addressing Noise in Multidialectal Word Embeddings
%A Erdmann, Alexander
%A Zalmout, Nasser
%A Habash, Nizar
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F erdmann-etal-2018-addressing
%X Word embeddings are crucial to many natural language processing tasks. The quality of embeddings relies on large non-noisy corpora. Arabic dialects lack large corpora and are noisy, being linguistically disparate with no standardized spelling. We make three contributions to address this noise. First, we describe simple but effective adaptations to word embedding tools to maximize the informative content leveraged in each training sentence. Second, we analyze methods for representing disparate dialects in one embedding space, either by mapping individual dialects into a shared space or learning a joint model of all dialects. Finally, we evaluate via dictionary induction, showing that two metrics not typically reported in the task enable us to analyze our contributions’ effects on low and high frequency words. In addition to boosting performance between 2-53%, we specifically improve on noisy, low frequency forms without compromising accuracy on high frequency forms.
%R 10.18653/v1/P18-2089
%U https://aclanthology.org/P18-2089
%U https://doi.org/10.18653/v1/P18-2089
%P 558-565
Markdown (Informal)
[Addressing Noise in Multidialectal Word Embeddings](https://aclanthology.org/P18-2089) (Erdmann et al., ACL 2018)
ACL
- Alexander Erdmann, Nasser Zalmout, and Nizar Habash. 2018. Addressing Noise in Multidialectal Word Embeddings. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 558–565, Melbourne, Australia. Association for Computational Linguistics.