@inproceedings{barbu-barbu-mititelu-2018-hybrid,
title = "A hybrid pipeline of rules and machine learning to filter web-crawled parallel corpora",
author = "Barbu, Eduard and
Barbu Mititelu, Verginica",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6474",
doi = "10.18653/v1/W18-6474",
pages = "867--871",
abstract = "A hybrid pipeline comprising rules and machine learning is used to filter a noisy web English-German parallel corpus for the Parallel Corpus Filtering task. The core of the pipeline is a module based on the logistic regression algorithm that returns the probability that a translation unit is accepted. The training set for the logistic regression is created by automatic annotation. The quality of the automatic annotation is estimated by manually labeling the training set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barbu-barbu-mititelu-2018-hybrid">
<titleInfo>
<title>A hybrid pipeline of rules and machine learning to filter web-crawled parallel corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Barbu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="family">Barbu Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A hybrid pipeline comprising rules and machine learning is used to filter a noisy web English-German parallel corpus for the Parallel Corpus Filtering task. The core of the pipeline is a module based on the logistic regression algorithm that returns the probability that a translation unit is accepted. The training set for the logistic regression is created by automatic annotation. The quality of the automatic annotation is estimated by manually labeling the training set.</abstract>
<identifier type="citekey">barbu-barbu-mititelu-2018-hybrid</identifier>
<identifier type="doi">10.18653/v1/W18-6474</identifier>
<location>
<url>https://aclanthology.org/W18-6474</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>867</start>
<end>871</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A hybrid pipeline of rules and machine learning to filter web-crawled parallel corpora
%A Barbu, Eduard
%A Barbu Mititelu, Verginica
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Belgium, Brussels
%F barbu-barbu-mititelu-2018-hybrid
%X A hybrid pipeline comprising rules and machine learning is used to filter a noisy web English-German parallel corpus for the Parallel Corpus Filtering task. The core of the pipeline is a module based on the logistic regression algorithm that returns the probability that a translation unit is accepted. The training set for the logistic regression is created by automatic annotation. The quality of the automatic annotation is estimated by manually labeling the training set.
%R 10.18653/v1/W18-6474
%U https://aclanthology.org/W18-6474
%U https://doi.org/10.18653/v1/W18-6474
%P 867-871
Markdown (Informal)
[A hybrid pipeline of rules and machine learning to filter web-crawled parallel corpora](https://aclanthology.org/W18-6474) (Barbu & Barbu Mititelu, 2018)
ACL