@inproceedings{michon-etal-2018-neural,
title = "Neural Network Architectures for {A}rabic Dialect Identification",
author = "Michon, Elise and
Pham, Minh Quang and
Crego, Josep and
Senellart, Jean",
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/W18-3914",
pages = "128--136",
abstract = "SYSTRAN competes this year for the first time to the DSL shared task, in the Arabic Dialect Identification subtask. We participate by training several Neural Network models showing that we can obtain competitive results despite the limited amount of training data available for learning. We report our experiments and detail the network architecture and parameters of our 3 runs: our best performing system consists in a Multi-Input CNN that learns separate embeddings for lexical, phonetic and acoustic input features (F1: 0.5289); we also built a CNN-biLSTM network aimed at capturing both spatial and sequential features directly from speech spectrograms (F1: 0.3894 at submission time, F1: 0.4235 with later found parameters); and finally a system relying on binary CNN-biLSTMs (F1: 0.4339).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="michon-etal-2018-neural">
<titleInfo>
<title>Neural Network Architectures for Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elise</namePart>
<namePart type="family">Michon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Quang</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josep</namePart>
<namePart type="family">Crego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean</namePart>
<namePart type="family">Senellart</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>SYSTRAN competes this year for the first time to the DSL shared task, in the Arabic Dialect Identification subtask. We participate by training several Neural Network models showing that we can obtain competitive results despite the limited amount of training data available for learning. We report our experiments and detail the network architecture and parameters of our 3 runs: our best performing system consists in a Multi-Input CNN that learns separate embeddings for lexical, phonetic and acoustic input features (F1: 0.5289); we also built a CNN-biLSTM network aimed at capturing both spatial and sequential features directly from speech spectrograms (F1: 0.3894 at submission time, F1: 0.4235 with later found parameters); and finally a system relying on binary CNN-biLSTMs (F1: 0.4339).</abstract>
<identifier type="citekey">michon-etal-2018-neural</identifier>
<location>
<url>https://aclanthology.org/W18-3914</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>128</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Network Architectures for Arabic Dialect Identification
%A Michon, Elise
%A Pham, Minh Quang
%A Crego, Josep
%A Senellart, Jean
%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 michon-etal-2018-neural
%X SYSTRAN competes this year for the first time to the DSL shared task, in the Arabic Dialect Identification subtask. We participate by training several Neural Network models showing that we can obtain competitive results despite the limited amount of training data available for learning. We report our experiments and detail the network architecture and parameters of our 3 runs: our best performing system consists in a Multi-Input CNN that learns separate embeddings for lexical, phonetic and acoustic input features (F1: 0.5289); we also built a CNN-biLSTM network aimed at capturing both spatial and sequential features directly from speech spectrograms (F1: 0.3894 at submission time, F1: 0.4235 with later found parameters); and finally a system relying on binary CNN-biLSTMs (F1: 0.4339).
%U https://aclanthology.org/W18-3914
%P 128-136
Markdown (Informal)
[Neural Network Architectures for Arabic Dialect Identification](https://aclanthology.org/W18-3914) (Michon et al., VarDial 2018)
ACL
- Elise Michon, Minh Quang Pham, Josep Crego, and Jean Senellart. 2018. Neural Network Architectures for Arabic Dialect Identification. In Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), pages 128–136, Santa Fe, New Mexico, USA. Association for Computational Linguistics.