@inproceedings{rabus-scherrer-2017-lexicon,
title = "Lexicon Induction for Spoken {R}usyn {--} Challenges and Results",
author = "Rabus, Achim and
Scherrer, Yves",
editor = "Erjavec, Toma{\v{z}} and
Piskorski, Jakub and
Pivovarova, Lidia and
{\v{S}}najder, Jan and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 6th Workshop on {B}alto-{S}lavic Natural Language Processing",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1405/",
doi = "10.18653/v1/W17-1405",
pages = "27--32",
abstract = "This paper reports on challenges and results in developing NLP resources for spoken Rusyn. Being a Slavic minority language, Rusyn does not have any resources to make use of. We propose to build a morphosyntactic dictionary for Rusyn, combining existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish. We adapt these resources to Rusyn by using vowel-sensitive Levenshtein distance, hand-written language-specific transformation rules, and combinations of the two. Compared to an exact match baseline, we increase the coverage of the resulting morphological dictionary by up to 77.4{\%} relative (42.9{\%} absolute), which results in a tagging recall increased by 11.6{\%} relative (9.1{\%} absolute). Our research confirms and expands the results of previous studies showing the efficiency of using NLP resources from neighboring languages for low-resourced languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rabus-scherrer-2017-lexicon">
<titleInfo>
<title>Lexicon Induction for Spoken Rusyn – Challenges and Results</title>
</titleInfo>
<name type="personal">
<namePart type="given">Achim</namePart>
<namePart type="family">Rabus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</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 6th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</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 reports on challenges and results in developing NLP resources for spoken Rusyn. Being a Slavic minority language, Rusyn does not have any resources to make use of. We propose to build a morphosyntactic dictionary for Rusyn, combining existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish. We adapt these resources to Rusyn by using vowel-sensitive Levenshtein distance, hand-written language-specific transformation rules, and combinations of the two. Compared to an exact match baseline, we increase the coverage of the resulting morphological dictionary by up to 77.4% relative (42.9% absolute), which results in a tagging recall increased by 11.6% relative (9.1% absolute). Our research confirms and expands the results of previous studies showing the efficiency of using NLP resources from neighboring languages for low-resourced languages.</abstract>
<identifier type="citekey">rabus-scherrer-2017-lexicon</identifier>
<identifier type="doi">10.18653/v1/W17-1405</identifier>
<location>
<url>https://aclanthology.org/W17-1405/</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>27</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexicon Induction for Spoken Rusyn – Challenges and Results
%A Rabus, Achim
%A Scherrer, Yves
%Y Erjavec, Tomaž
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Šnajder, Jan
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F rabus-scherrer-2017-lexicon
%X This paper reports on challenges and results in developing NLP resources for spoken Rusyn. Being a Slavic minority language, Rusyn does not have any resources to make use of. We propose to build a morphosyntactic dictionary for Rusyn, combining existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish. We adapt these resources to Rusyn by using vowel-sensitive Levenshtein distance, hand-written language-specific transformation rules, and combinations of the two. Compared to an exact match baseline, we increase the coverage of the resulting morphological dictionary by up to 77.4% relative (42.9% absolute), which results in a tagging recall increased by 11.6% relative (9.1% absolute). Our research confirms and expands the results of previous studies showing the efficiency of using NLP resources from neighboring languages for low-resourced languages.
%R 10.18653/v1/W17-1405
%U https://aclanthology.org/W17-1405/
%U https://doi.org/10.18653/v1/W17-1405
%P 27-32
Markdown (Informal)
[Lexicon Induction for Spoken Rusyn – Challenges and Results](https://aclanthology.org/W17-1405/) (Rabus & Scherrer, BSNLP 2017)
ACL