@inproceedings{mikhailov-etal-2019-initial,
title = "Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation",
author = "Mikhailov, Vladislav and
Tosi, Lorenzo and
Khorosheva, Anastasia and
Serikov, Oleg",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Malmasi, Shervin and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Ali, Ahmed},
booktitle = "Proceedings of the Sixth Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = jun,
year = "2019",
address = "Ann Arbor, Michigan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1415",
doi = "10.18653/v1/W19-1415",
pages = "144--152",
abstract = "The paper describes initial experiments in data-driven cross-lingual morphological analysis of open-category words using a combination of unsupervised morpheme segmentation, annotation projection and an LSTM encoder-decoder model with attention. Our algorithm provides lemmatisation and morphological analysis generation for previously unseen low-resource language surface forms with only annotated data on the related languages given. Despite the inherently lossy annotation projection, we achieved the best lemmatisation F1-score in the VarDial 2019 Shared Task on Cross-Lingual Morphological Analysis for both Karachay-Balkar (Turkic languages, agglutinative morphology) and Sardinian (Romance languages, fusional morphology).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mikhailov-etal-2019-initial">
<titleInfo>
<title>Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Tosi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Khorosheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Ann Arbor, Michigan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper describes initial experiments in data-driven cross-lingual morphological analysis of open-category words using a combination of unsupervised morpheme segmentation, annotation projection and an LSTM encoder-decoder model with attention. Our algorithm provides lemmatisation and morphological analysis generation for previously unseen low-resource language surface forms with only annotated data on the related languages given. Despite the inherently lossy annotation projection, we achieved the best lemmatisation F1-score in the VarDial 2019 Shared Task on Cross-Lingual Morphological Analysis for both Karachay-Balkar (Turkic languages, agglutinative morphology) and Sardinian (Romance languages, fusional morphology).</abstract>
<identifier type="citekey">mikhailov-etal-2019-initial</identifier>
<identifier type="doi">10.18653/v1/W19-1415</identifier>
<location>
<url>https://aclanthology.org/W19-1415</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>144</start>
<end>152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation
%A Mikhailov, Vladislav
%A Tosi, Lorenzo
%A Khorosheva, Anastasia
%A Serikov, Oleg
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Malmasi, Shervin
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Ali, Ahmed
%S Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2019
%8 June
%I Association for Computational Linguistics
%C Ann Arbor, Michigan
%F mikhailov-etal-2019-initial
%X The paper describes initial experiments in data-driven cross-lingual morphological analysis of open-category words using a combination of unsupervised morpheme segmentation, annotation projection and an LSTM encoder-decoder model with attention. Our algorithm provides lemmatisation and morphological analysis generation for previously unseen low-resource language surface forms with only annotated data on the related languages given. Despite the inherently lossy annotation projection, we achieved the best lemmatisation F1-score in the VarDial 2019 Shared Task on Cross-Lingual Morphological Analysis for both Karachay-Balkar (Turkic languages, agglutinative morphology) and Sardinian (Romance languages, fusional morphology).
%R 10.18653/v1/W19-1415
%U https://aclanthology.org/W19-1415
%U https://doi.org/10.18653/v1/W19-1415
%P 144-152
Markdown (Informal)
[Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation](https://aclanthology.org/W19-1415) (Mikhailov et al., VarDial 2019)
ACL