@inproceedings{hoya-quecedo-etal-2020-neural,
title = "Neural Disambiguation of Lemma and Part of Speech in Morphologically Rich Languages",
author = "Hoya Quecedo, Jos{\'e} Mar{\'\i}a and
Maximilian, Koppatz and
Yangarber, Roman",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.439",
pages = "3573--3582",
abstract = "We consider the problem of disambiguating the lemma and part of speech of ambiguous words in morphologically rich languages. We propose a method for disambiguating ambiguous words in context, using a large un-annotated corpus of text, and a morphological analyser{---}with no manual disambiguation or data annotation. We assume that the morphological analyser produces multiple analyses for ambiguous words. The idea is to train recurrent neural networks on the output that the morphological analyser produces for unambiguous words. We present performance on POS and lemma disambiguation that reaches or surpasses the state of the art{---}including supervised models{---}using no manually annotated data. We evaluate the method on several morphologically rich languages.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoya-quecedo-etal-2020-neural">
<titleInfo>
<title>Neural Disambiguation of Lemma and Part of Speech in Morphologically Rich Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">María</namePart>
<namePart type="family">Hoya Quecedo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koppatz</namePart>
<namePart type="family">Maximilian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We consider the problem of disambiguating the lemma and part of speech of ambiguous words in morphologically rich languages. We propose a method for disambiguating ambiguous words in context, using a large un-annotated corpus of text, and a morphological analyser—with no manual disambiguation or data annotation. We assume that the morphological analyser produces multiple analyses for ambiguous words. The idea is to train recurrent neural networks on the output that the morphological analyser produces for unambiguous words. We present performance on POS and lemma disambiguation that reaches or surpasses the state of the art—including supervised models—using no manually annotated data. We evaluate the method on several morphologically rich languages.</abstract>
<identifier type="citekey">hoya-quecedo-etal-2020-neural</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.439</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>3573</start>
<end>3582</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Disambiguation of Lemma and Part of Speech in Morphologically Rich Languages
%A Hoya Quecedo, José María
%A Maximilian, Koppatz
%A Yangarber, Roman
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F hoya-quecedo-etal-2020-neural
%X We consider the problem of disambiguating the lemma and part of speech of ambiguous words in morphologically rich languages. We propose a method for disambiguating ambiguous words in context, using a large un-annotated corpus of text, and a morphological analyser—with no manual disambiguation or data annotation. We assume that the morphological analyser produces multiple analyses for ambiguous words. The idea is to train recurrent neural networks on the output that the morphological analyser produces for unambiguous words. We present performance on POS and lemma disambiguation that reaches or surpasses the state of the art—including supervised models—using no manually annotated data. We evaluate the method on several morphologically rich languages.
%U https://aclanthology.org/2020.lrec-1.439
%P 3573-3582
Markdown (Informal)
[Neural Disambiguation of Lemma and Part of Speech in Morphologically Rich Languages](https://aclanthology.org/2020.lrec-1.439) (Hoya Quecedo et al., LREC 2020)
ACL