@inproceedings{scherrer-rabus-2017-multi,
title = "Multi-source morphosyntactic tagging for spoken {R}usyn",
author = "Scherrer, Yves and
Rabus, Achim",
editor = {Nakov, Preslav and
Zampieri, Marcos and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shevin and
Ali, Ahmed},
booktitle = "Proceedings of the Fourth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial)",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1210",
doi = "10.18653/v1/W17-1210",
pages = "84--92",
abstract = "This paper deals with the development of morphosyntactic taggers for spoken varieties of the Slavic minority language Rusyn. As neither annotated corpora nor parallel corpora are electronically available for Rusyn, we propose to combine existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish and adapt them to Rusyn. Using MarMoT as tagging toolkit, we show that a tagger trained on a balanced set of the four source languages outperforms single language taggers by about 9{\%}, and that additional automatically induced morphosyntactic lexicons lead to further improvements. The best observed accuracies for Rusyn are 82.4{\%} for part-of-speech tagging and 75.5{\%} for full morphological tagging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scherrer-rabus-2017-multi">
<titleInfo>
<title>Multi-source morphosyntactic tagging for spoken Rusyn</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Achim</namePart>
<namePart type="family">Rabus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)</title>
</titleInfo>
<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">Marcos</namePart>
<namePart type="family">Zampieri</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">Shevin</namePart>
<namePart type="family">Malmasi</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">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper deals with the development of morphosyntactic taggers for spoken varieties of the Slavic minority language Rusyn. As neither annotated corpora nor parallel corpora are electronically available for Rusyn, we propose to combine existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish and adapt them to Rusyn. Using MarMoT as tagging toolkit, we show that a tagger trained on a balanced set of the four source languages outperforms single language taggers by about 9%, and that additional automatically induced morphosyntactic lexicons lead to further improvements. The best observed accuracies for Rusyn are 82.4% for part-of-speech tagging and 75.5% for full morphological tagging.</abstract>
<identifier type="citekey">scherrer-rabus-2017-multi</identifier>
<identifier type="doi">10.18653/v1/W17-1210</identifier>
<location>
<url>https://aclanthology.org/W17-1210</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>84</start>
<end>92</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-source morphosyntactic tagging for spoken Rusyn
%A Scherrer, Yves
%A Rabus, Achim
%Y Nakov, Preslav
%Y Zampieri, Marcos
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shevin
%Y Ali, Ahmed
%S Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F scherrer-rabus-2017-multi
%X This paper deals with the development of morphosyntactic taggers for spoken varieties of the Slavic minority language Rusyn. As neither annotated corpora nor parallel corpora are electronically available for Rusyn, we propose to combine existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish and adapt them to Rusyn. Using MarMoT as tagging toolkit, we show that a tagger trained on a balanced set of the four source languages outperforms single language taggers by about 9%, and that additional automatically induced morphosyntactic lexicons lead to further improvements. The best observed accuracies for Rusyn are 82.4% for part-of-speech tagging and 75.5% for full morphological tagging.
%R 10.18653/v1/W17-1210
%U https://aclanthology.org/W17-1210
%U https://doi.org/10.18653/v1/W17-1210
%P 84-92
Markdown (Informal)
[Multi-source morphosyntactic tagging for spoken Rusyn](https://aclanthology.org/W17-1210) (Scherrer & Rabus, VarDial 2017)
ACL
- Yves Scherrer and Achim Rabus. 2017. Multi-source morphosyntactic tagging for spoken Rusyn. In Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), pages 84–92, Valencia, Spain. Association for Computational Linguistics.