@inproceedings{hamalainen-etal-2021-neural,
title = "Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered",
author = {H{\"a}m{\"a}l{\"a}inen, Mika and
Partanen, Niko and
Rueter, Jack and
Alnajjar, Khalid},
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.17",
pages = "166--177",
abstract = "We train neural models for morphological analysis, generation and lemmatization for morphologically rich languages. We present a method for automatically extracting substantially large amount of training data from FSTs for 22 languages, out of which 17 are endangered. The neural models follow the same tagset as the FSTs in order to make it possible to use them as fallback systems together with the FSTs. The source code, models and datasets have been released on Zenodo.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamalainen-etal-2021-neural">
<titleInfo>
<title>Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="family">Partanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may" 31–2 "jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We train neural models for morphological analysis, generation and lemmatization for morphologically rich languages. We present a method for automatically extracting substantially large amount of training data from FSTs for 22 languages, out of which 17 are endangered. The neural models follow the same tagset as the FSTs in order to make it possible to use them as fallback systems together with the FSTs. The source code, models and datasets have been released on Zenodo.</abstract>
<identifier type="citekey">hamalainen-etal-2021-neural</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.17</url>
</location>
<part>
<date>2021-may" 31–2 "jun</date>
<extent unit="page">
<start>166</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered
%A Hämäläinen, Mika
%A Partanen, Niko
%A Rueter, Jack
%A Alnajjar, Khalid
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may" 31–2 "jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F hamalainen-etal-2021-neural
%X We train neural models for morphological analysis, generation and lemmatization for morphologically rich languages. We present a method for automatically extracting substantially large amount of training data from FSTs for 22 languages, out of which 17 are endangered. The neural models follow the same tagset as the FSTs in order to make it possible to use them as fallback systems together with the FSTs. The source code, models and datasets have been released on Zenodo.
%U https://aclanthology.org/2021.nodalida-main.17
%P 166-177
Markdown (Informal)
[Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered](https://aclanthology.org/2021.nodalida-main.17) (Hämäläinen et al., NoDaLiDa 2021)
ACL