@inproceedings{lo-joanis-2020-improving,
title = "Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language Models",
author = "Lo, Chi-kiu and
Joanis, Eric",
editor = {Barrault, Lo{\"\i}c and
Bojar, Ond{\v{r}}ej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-juss{\`a}, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Graham, Yvette and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Morishita, Makoto and
Monz, Christof and
Nagata, Masaaki and
Nakazawa, Toshiaki and
Negri, Matteo},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.110",
pages = "972--978",
abstract = "The National Research Council of Canada{'}s team submissions to the parallel corpus filtering task at the Fifth Conference on Machine Translation are based on two key components: (1) iteratively refined statistical sentence alignments for extracting sentence pairs from document pairs and (2) a crosslingual semantic textual similarity metric based on a pretrained multilingual language model, XLM-RoBERTa, with bilingual mappings learnt from a minimal amount of clean parallel data for scoring the parallelism of the extracted sentence pairs. The translation quality of the neural machine translation systems trained and fine-tuned on the parallel data extracted by our submissions improved significantly when compared to the organizers{'} LASER-based baseline, a sentence-embedding method that worked well last year. For re-aligning the sentences in the document pairs (component 1), our statistical approach has outperformed the current state-of-the-art neural approach in this low-resource context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lo-joanis-2020-improving">
<titleInfo>
<title>Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chi-kiu</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Joanis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The National Research Council of Canada’s team submissions to the parallel corpus filtering task at the Fifth Conference on Machine Translation are based on two key components: (1) iteratively refined statistical sentence alignments for extracting sentence pairs from document pairs and (2) a crosslingual semantic textual similarity metric based on a pretrained multilingual language model, XLM-RoBERTa, with bilingual mappings learnt from a minimal amount of clean parallel data for scoring the parallelism of the extracted sentence pairs. The translation quality of the neural machine translation systems trained and fine-tuned on the parallel data extracted by our submissions improved significantly when compared to the organizers’ LASER-based baseline, a sentence-embedding method that worked well last year. For re-aligning the sentences in the document pairs (component 1), our statistical approach has outperformed the current state-of-the-art neural approach in this low-resource context.</abstract>
<identifier type="citekey">lo-joanis-2020-improving</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.110</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>972</start>
<end>978</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language Models
%A Lo, Chi-kiu
%A Joanis, Eric
%Y Barrault, Loïc
%Y Bojar, Ondřej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussà, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Graham, Yvette
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Morishita, Makoto
%Y Monz, Christof
%Y Nagata, Masaaki
%Y Nakazawa, Toshiaki
%Y Negri, Matteo
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F lo-joanis-2020-improving
%X The National Research Council of Canada’s team submissions to the parallel corpus filtering task at the Fifth Conference on Machine Translation are based on two key components: (1) iteratively refined statistical sentence alignments for extracting sentence pairs from document pairs and (2) a crosslingual semantic textual similarity metric based on a pretrained multilingual language model, XLM-RoBERTa, with bilingual mappings learnt from a minimal amount of clean parallel data for scoring the parallelism of the extracted sentence pairs. The translation quality of the neural machine translation systems trained and fine-tuned on the parallel data extracted by our submissions improved significantly when compared to the organizers’ LASER-based baseline, a sentence-embedding method that worked well last year. For re-aligning the sentences in the document pairs (component 1), our statistical approach has outperformed the current state-of-the-art neural approach in this low-resource context.
%U https://aclanthology.org/2020.wmt-1.110
%P 972-978
Markdown (Informal)
[Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language Models](https://aclanthology.org/2020.wmt-1.110) (Lo & Joanis, WMT 2020)
ACL