@inproceedings{erdmann-etal-2019-little,
title = "A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance",
author = "Erdmann, Alexander and
Khalifa, Salam and
Oudah, Mai and
Habash, Nizar and
Bouamor, Houda",
editor = "Nicolai, Garrett and
Cotterell, Ryan",
booktitle = "Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4214",
doi = "10.18653/v1/W19-4214",
pages = "113--124",
abstract = "We present de-lexical segmentation, a linguistically motivated alternative to greedy or other unsupervised methods, requiring only minimal language specific input. Our technique involves creating a small grammar of closed-class affixes which can be written in a few hours. The grammar over generates analyses for word forms attested in a raw corpus which are disambiguated based on features of the linguistic base proposed for each form. Extending the grammar to cover orthographic, morpho-syntactic or lexical variation is simple, making it an ideal solution for challenging corpora with noisy, dialect-inconsistent, or otherwise non-standard content. In two evaluations, we consistently outperform competitive unsupervised baselines and approach the performance of state-of-the-art supervised models trained on large amounts of data, providing evidence for the value of linguistic input during preprocessing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="erdmann-etal-2019-little">
<titleInfo>
<title>A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance</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">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mai</namePart>
<namePart type="family">Oudah</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>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present de-lexical segmentation, a linguistically motivated alternative to greedy or other unsupervised methods, requiring only minimal language specific input. Our technique involves creating a small grammar of closed-class affixes which can be written in a few hours. The grammar over generates analyses for word forms attested in a raw corpus which are disambiguated based on features of the linguistic base proposed for each form. Extending the grammar to cover orthographic, morpho-syntactic or lexical variation is simple, making it an ideal solution for challenging corpora with noisy, dialect-inconsistent, or otherwise non-standard content. In two evaluations, we consistently outperform competitive unsupervised baselines and approach the performance of state-of-the-art supervised models trained on large amounts of data, providing evidence for the value of linguistic input during preprocessing.</abstract>
<identifier type="citekey">erdmann-etal-2019-little</identifier>
<identifier type="doi">10.18653/v1/W19-4214</identifier>
<location>
<url>https://aclanthology.org/W19-4214</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>113</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance
%A Erdmann, Alexander
%A Khalifa, Salam
%A Oudah, Mai
%A Habash, Nizar
%A Bouamor, Houda
%Y Nicolai, Garrett
%Y Cotterell, Ryan
%S Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F erdmann-etal-2019-little
%X We present de-lexical segmentation, a linguistically motivated alternative to greedy or other unsupervised methods, requiring only minimal language specific input. Our technique involves creating a small grammar of closed-class affixes which can be written in a few hours. The grammar over generates analyses for word forms attested in a raw corpus which are disambiguated based on features of the linguistic base proposed for each form. Extending the grammar to cover orthographic, morpho-syntactic or lexical variation is simple, making it an ideal solution for challenging corpora with noisy, dialect-inconsistent, or otherwise non-standard content. In two evaluations, we consistently outperform competitive unsupervised baselines and approach the performance of state-of-the-art supervised models trained on large amounts of data, providing evidence for the value of linguistic input during preprocessing.
%R 10.18653/v1/W19-4214
%U https://aclanthology.org/W19-4214
%U https://doi.org/10.18653/v1/W19-4214
%P 113-124
Markdown (Informal)
[A Little Linguistics Goes a Long Way: Unsupervised Segmentation with Limited Language Specific Guidance](https://aclanthology.org/W19-4214) (Erdmann et al., ACL 2019)
ACL