@inproceedings{meftah-etal-2018-using,
title = "Using Neural Transfer Learning for Morpho-syntactic Tagging of {S}outh-{S}lavic Languages Tweets",
author = "Meftah, Sara and
Semmar, Nasredine and
Sadat, Fatiha and
Raaijmakers, Stephan",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin and
Ali, Ahmed},
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial 2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3927",
pages = "235--243",
abstract = "In this paper, we describe a morpho-syntactic tagger of tweets, an important component of the CEA List DeepLIMA tool which is a multilingual text analysis platform based on deep learning. This tagger is built for the Morpho-syntactic Tagging of Tweets (MTT) Shared task of the 2018 VarDial Evaluation Campaign. The MTT task focuses on morpho-syntactic annotation of non-canonical Twitter varieties of three South-Slavic languages: Slovene, Croatian and Serbian. We propose to use a neural network model trained in an end-to-end manner for the three languages without any need for task or domain specific features engineering. The proposed approach combines both character and word level representations. Considering the lack of annotated data in the social media domain for South-Slavic languages, we have also implemented a cross-domain Transfer Learning (TL) approach to exploit any available related out-of-domain annotated data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meftah-etal-2018-using">
<titleInfo>
<title>Using Neural Transfer Learning for Morpho-syntactic Tagging of South-Slavic Languages Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Meftah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nasredine</namePart>
<namePart type="family">Semmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatiha</namePart>
<namePart type="family">Sadat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Raaijmakers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)</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">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">Shervin</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">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe a morpho-syntactic tagger of tweets, an important component of the CEA List DeepLIMA tool which is a multilingual text analysis platform based on deep learning. This tagger is built for the Morpho-syntactic Tagging of Tweets (MTT) Shared task of the 2018 VarDial Evaluation Campaign. The MTT task focuses on morpho-syntactic annotation of non-canonical Twitter varieties of three South-Slavic languages: Slovene, Croatian and Serbian. We propose to use a neural network model trained in an end-to-end manner for the three languages without any need for task or domain specific features engineering. The proposed approach combines both character and word level representations. Considering the lack of annotated data in the social media domain for South-Slavic languages, we have also implemented a cross-domain Transfer Learning (TL) approach to exploit any available related out-of-domain annotated data.</abstract>
<identifier type="citekey">meftah-etal-2018-using</identifier>
<location>
<url>https://aclanthology.org/W18-3927</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>235</start>
<end>243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Neural Transfer Learning for Morpho-syntactic Tagging of South-Slavic Languages Tweets
%A Meftah, Sara
%A Semmar, Nasredine
%A Sadat, Fatiha
%A Raaijmakers, Stephan
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%Y Ali, Ahmed
%S Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F meftah-etal-2018-using
%X In this paper, we describe a morpho-syntactic tagger of tweets, an important component of the CEA List DeepLIMA tool which is a multilingual text analysis platform based on deep learning. This tagger is built for the Morpho-syntactic Tagging of Tweets (MTT) Shared task of the 2018 VarDial Evaluation Campaign. The MTT task focuses on morpho-syntactic annotation of non-canonical Twitter varieties of three South-Slavic languages: Slovene, Croatian and Serbian. We propose to use a neural network model trained in an end-to-end manner for the three languages without any need for task or domain specific features engineering. The proposed approach combines both character and word level representations. Considering the lack of annotated data in the social media domain for South-Slavic languages, we have also implemented a cross-domain Transfer Learning (TL) approach to exploit any available related out-of-domain annotated data.
%U https://aclanthology.org/W18-3927
%P 235-243
Markdown (Informal)
[Using Neural Transfer Learning for Morpho-syntactic Tagging of South-Slavic Languages Tweets](https://aclanthology.org/W18-3927) (Meftah et al., VarDial 2018)
ACL