@inproceedings{tambouratzis-pouli-2016-linguistically,
title = "Linguistically Inspired Language Model Augmentation for {MT}",
author = "Tambouratzis, George and
Pouli, Vasiliki",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1091",
pages = "573--577",
abstract = "The present article reports on efforts to improve the translation accuracy of a corpus―based Machine Translation (MT) system. In order to achieve that, an error analysis performed on past translation outputs has indicated the likelihood of improving the translation accuracy by augmenting the coverage of the Target-Language (TL) side language model. The method adopted for improving the language model is initially presented, based on the concatenation of consecutive phrases. The algorithmic steps are then described that form the process for augmenting the language model. The key idea is to only augment the language model to cover the most frequent cases of phrase sequences, as counted over a TL-side corpus, in order to maximize the cases covered by the new language model entries. Experiments presented in the article show that substantial improvements in translation accuracy are achieved via the proposed method, when integrating the grown language model to the corpus-based MT system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tambouratzis-pouli-2016-linguistically">
<titleInfo>
<title>Linguistically Inspired Language Model Augmentation for MT</title>
</titleInfo>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Tambouratzis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasiliki</namePart>
<namePart type="family">Pouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The present article reports on efforts to improve the translation accuracy of a corpus―based Machine Translation (MT) system. In order to achieve that, an error analysis performed on past translation outputs has indicated the likelihood of improving the translation accuracy by augmenting the coverage of the Target-Language (TL) side language model. The method adopted for improving the language model is initially presented, based on the concatenation of consecutive phrases. The algorithmic steps are then described that form the process for augmenting the language model. The key idea is to only augment the language model to cover the most frequent cases of phrase sequences, as counted over a TL-side corpus, in order to maximize the cases covered by the new language model entries. Experiments presented in the article show that substantial improvements in translation accuracy are achieved via the proposed method, when integrating the grown language model to the corpus-based MT system.</abstract>
<identifier type="citekey">tambouratzis-pouli-2016-linguistically</identifier>
<location>
<url>https://aclanthology.org/L16-1091</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>573</start>
<end>577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistically Inspired Language Model Augmentation for MT
%A Tambouratzis, George
%A Pouli, Vasiliki
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F tambouratzis-pouli-2016-linguistically
%X The present article reports on efforts to improve the translation accuracy of a corpus―based Machine Translation (MT) system. In order to achieve that, an error analysis performed on past translation outputs has indicated the likelihood of improving the translation accuracy by augmenting the coverage of the Target-Language (TL) side language model. The method adopted for improving the language model is initially presented, based on the concatenation of consecutive phrases. The algorithmic steps are then described that form the process for augmenting the language model. The key idea is to only augment the language model to cover the most frequent cases of phrase sequences, as counted over a TL-side corpus, in order to maximize the cases covered by the new language model entries. Experiments presented in the article show that substantial improvements in translation accuracy are achieved via the proposed method, when integrating the grown language model to the corpus-based MT system.
%U https://aclanthology.org/L16-1091
%P 573-577
Markdown (Informal)
[Linguistically Inspired Language Model Augmentation for MT](https://aclanthology.org/L16-1091) (Tambouratzis & Pouli, LREC 2016)
ACL