@inproceedings{ballier-etal-2020-learnability,
title = "The Learnability of the Annotated Input in {NMT} Replicating (Vanmassenhove and Way, 2018) with {O}pen{NMT}",
author = "Ballier, Nicolas and
Amari, Nabil and
Merat, Laure and
Yun{\`e}s, Jean-Baptiste",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.691",
pages = "5631--5640",
abstract = "In this paper, we reproduce some of the experiments related to neural network training for Machine Translation as reported in (Vanmassenhove and Way, 2018). They annotated a sample from the EN-FR and EN-DE Europarl aligned corpora with syntactic and semantic annotations to train neural networks with the Nematus Neural Machine Translation (NMT) toolkit. Following the original publication, we obtained lower BLEU scores than the authors of the original paper, but on a more limited set of annotations. In the second half of the paper, we try to analyze the difference in the results obtained and suggest some methods to improve the results. We discuss the Byte Pair Encoding (BPE) used in the pre-processing phase and suggest feature ablation in relation to the granularity of syntactic and semantic annotations. The learnability of the annotated input is discussed in relation to existing resources for the target languages. We also discuss the feature representation likely to have been adopted for combining features.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ballier-etal-2020-learnability">
<titleInfo>
<title>The Learnability of the Annotated Input in NMT Replicating (Vanmassenhove and Way, 2018) with OpenNMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Ballier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nabil</namePart>
<namePart type="family">Amari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laure</namePart>
<namePart type="family">Merat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Baptiste</namePart>
<namePart type="family">Yunès</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, we reproduce some of the experiments related to neural network training for Machine Translation as reported in (Vanmassenhove and Way, 2018). They annotated a sample from the EN-FR and EN-DE Europarl aligned corpora with syntactic and semantic annotations to train neural networks with the Nematus Neural Machine Translation (NMT) toolkit. Following the original publication, we obtained lower BLEU scores than the authors of the original paper, but on a more limited set of annotations. In the second half of the paper, we try to analyze the difference in the results obtained and suggest some methods to improve the results. We discuss the Byte Pair Encoding (BPE) used in the pre-processing phase and suggest feature ablation in relation to the granularity of syntactic and semantic annotations. The learnability of the annotated input is discussed in relation to existing resources for the target languages. We also discuss the feature representation likely to have been adopted for combining features.</abstract>
<identifier type="citekey">ballier-etal-2020-learnability</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.691</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5631</start>
<end>5640</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Learnability of the Annotated Input in NMT Replicating (Vanmassenhove and Way, 2018) with OpenNMT
%A Ballier, Nicolas
%A Amari, Nabil
%A Merat, Laure
%A Yunès, Jean-Baptiste
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F ballier-etal-2020-learnability
%X In this paper, we reproduce some of the experiments related to neural network training for Machine Translation as reported in (Vanmassenhove and Way, 2018). They annotated a sample from the EN-FR and EN-DE Europarl aligned corpora with syntactic and semantic annotations to train neural networks with the Nematus Neural Machine Translation (NMT) toolkit. Following the original publication, we obtained lower BLEU scores than the authors of the original paper, but on a more limited set of annotations. In the second half of the paper, we try to analyze the difference in the results obtained and suggest some methods to improve the results. We discuss the Byte Pair Encoding (BPE) used in the pre-processing phase and suggest feature ablation in relation to the granularity of syntactic and semantic annotations. The learnability of the annotated input is discussed in relation to existing resources for the target languages. We also discuss the feature representation likely to have been adopted for combining features.
%U https://aclanthology.org/2020.lrec-1.691
%P 5631-5640
Markdown (Informal)
[The Learnability of the Annotated Input in NMT Replicating (Vanmassenhove and Way, 2018) with OpenNMT](https://aclanthology.org/2020.lrec-1.691) (Ballier et al., LREC 2020)
ACL