@inproceedings{ljubesic-dobrovoljc-2019-neural,
title = "What does Neural Bring? Analysing Improvements in Morphosyntactic Annotation and Lemmatisation of {S}lovenian, {C}roatian and {S}erbian",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Dobrovoljc, Kaja",
editor = "Erjavec, Toma{\v{z}} and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Piskorski, Jakub and
Pivovarova, Lidia and
{\v{S}}najder, Jan and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3704",
doi = "10.18653/v1/W19-3704",
pages = "29--34",
abstract = "We present experiments on Slovenian, Croatian and Serbian morphosyntactic annotation and lemmatisation between the former state-of-the-art for these three languages and one of the best performing systems at the CoNLL 2018 shared task, the Stanford NLP neural pipeline. Our experiments show significant improvements in morphosyntactic annotation, especially on categories where either semantic knowledge is needed, available through word embeddings, or where long-range dependencies have to be modelled. On the other hand, on the task of lemmatisation no improvements are obtained with the neural solution, mostly due to the heavy dependence of the task on the lookup in an external lexicon, but also due to obvious room for improvements in the Stanford NLP pipeline{'}s lemmatisation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-dobrovoljc-2019-neural">
<titleInfo>
<title>What does Neural Bring? Analysing Improvements in Morphosyntactic Annotation and Lemmatisation of Slovenian, Croatian and Serbian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaja</namePart>
<namePart type="family">Dobrovoljc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th 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">Michał</namePart>
<namePart type="family">Marcińczuk</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">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">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present experiments on Slovenian, Croatian and Serbian morphosyntactic annotation and lemmatisation between the former state-of-the-art for these three languages and one of the best performing systems at the CoNLL 2018 shared task, the Stanford NLP neural pipeline. Our experiments show significant improvements in morphosyntactic annotation, especially on categories where either semantic knowledge is needed, available through word embeddings, or where long-range dependencies have to be modelled. On the other hand, on the task of lemmatisation no improvements are obtained with the neural solution, mostly due to the heavy dependence of the task on the lookup in an external lexicon, but also due to obvious room for improvements in the Stanford NLP pipeline’s lemmatisation.</abstract>
<identifier type="citekey">ljubesic-dobrovoljc-2019-neural</identifier>
<identifier type="doi">10.18653/v1/W19-3704</identifier>
<location>
<url>https://aclanthology.org/W19-3704</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>29</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What does Neural Bring? Analysing Improvements in Morphosyntactic Annotation and Lemmatisation of Slovenian, Croatian and Serbian
%A Ljubešić, Nikola
%A Dobrovoljc, Kaja
%Y Erjavec, Tomaž
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Šnajder, Jan
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F ljubesic-dobrovoljc-2019-neural
%X We present experiments on Slovenian, Croatian and Serbian morphosyntactic annotation and lemmatisation between the former state-of-the-art for these three languages and one of the best performing systems at the CoNLL 2018 shared task, the Stanford NLP neural pipeline. Our experiments show significant improvements in morphosyntactic annotation, especially on categories where either semantic knowledge is needed, available through word embeddings, or where long-range dependencies have to be modelled. On the other hand, on the task of lemmatisation no improvements are obtained with the neural solution, mostly due to the heavy dependence of the task on the lookup in an external lexicon, but also due to obvious room for improvements in the Stanford NLP pipeline’s lemmatisation.
%R 10.18653/v1/W19-3704
%U https://aclanthology.org/W19-3704
%U https://doi.org/10.18653/v1/W19-3704
%P 29-34
Markdown (Informal)
[What does Neural Bring? Analysing Improvements in Morphosyntactic Annotation and Lemmatisation of Slovenian, Croatian and Serbian](https://aclanthology.org/W19-3704) (Ljubešić & Dobrovoljc, BSNLP 2019)
ACL