@inproceedings{chatterjee-etal-2016-instance,
title = "Instance Selection for Online Automatic Post-Editing in a multi-domain scenario",
author = "Chatterjee, Rajen and
Arcan, Mihael and
Negri, Matteo and
Turchi, Marco",
editor = "Green, Spence and
Schwartz, Lane",
booktitle = "Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track",
month = oct # " 28 - " # nov # " 1",
year = "2016",
address = "Austin, TX, USA",
publisher = "The Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2016.amta-researchers.1",
pages = "1--15",
abstract = "In recent years, several end-to-end online translation systems have been proposed to successfully incorporate human post-editing feedback in the translation workflow. The performance of these systems in a multi-domain translation environment (involving different text genres, post-editing styles, machine translation systems) within the automatic post-editing (APE) task has not been thoroughly investigated yet. In this work, we show that when used in the APE framework the existing online systems are not robust towards domain changes in the incoming data stream. In particular, these systems lack in the capability to learn and use domain-specific post-editing rules from a pool of multi-domain data sets. To cope with this problem, we propose an online learning framework that generates more reliable translations with significantly better quality as compared with the existing online and batch systems. Our framework includes: i) an instance selection technique based on information retrieval that helps to build domain-specific APE systems, and ii) an optimization procedure to tune the feature weights of the log-linear model that allows the decoder to improve the post-editing quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chatterjee-etal-2016-instance">
<titleInfo>
<title>Instance Selection for Online Automatic Post-Editing in a multi-domain scenario</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihael</namePart>
<namePart type="family">Arcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-oct 28 - nov 1</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Conferences of the Association for Machine Translation in the Americas: MT Researchers’ Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spence</namePart>
<namePart type="family">Green</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Austin, TX, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, several end-to-end online translation systems have been proposed to successfully incorporate human post-editing feedback in the translation workflow. The performance of these systems in a multi-domain translation environment (involving different text genres, post-editing styles, machine translation systems) within the automatic post-editing (APE) task has not been thoroughly investigated yet. In this work, we show that when used in the APE framework the existing online systems are not robust towards domain changes in the incoming data stream. In particular, these systems lack in the capability to learn and use domain-specific post-editing rules from a pool of multi-domain data sets. To cope with this problem, we propose an online learning framework that generates more reliable translations with significantly better quality as compared with the existing online and batch systems. Our framework includes: i) an instance selection technique based on information retrieval that helps to build domain-specific APE systems, and ii) an optimization procedure to tune the feature weights of the log-linear model that allows the decoder to improve the post-editing quality.</abstract>
<identifier type="citekey">chatterjee-etal-2016-instance</identifier>
<location>
<url>https://aclanthology.org/2016.amta-researchers.1</url>
</location>
<part>
<date>2016-oct 28 - nov 1</date>
<extent unit="page">
<start>1</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Instance Selection for Online Automatic Post-Editing in a multi-domain scenario
%A Chatterjee, Rajen
%A Arcan, Mihael
%A Negri, Matteo
%A Turchi, Marco
%Y Green, Spence
%Y Schwartz, Lane
%S Conferences of the Association for Machine Translation in the Americas: MT Researchers’ Track
%D 2016
%8 oct 28 nov 1
%I The Association for Machine Translation in the Americas
%C Austin, TX, USA
%F chatterjee-etal-2016-instance
%X In recent years, several end-to-end online translation systems have been proposed to successfully incorporate human post-editing feedback in the translation workflow. The performance of these systems in a multi-domain translation environment (involving different text genres, post-editing styles, machine translation systems) within the automatic post-editing (APE) task has not been thoroughly investigated yet. In this work, we show that when used in the APE framework the existing online systems are not robust towards domain changes in the incoming data stream. In particular, these systems lack in the capability to learn and use domain-specific post-editing rules from a pool of multi-domain data sets. To cope with this problem, we propose an online learning framework that generates more reliable translations with significantly better quality as compared with the existing online and batch systems. Our framework includes: i) an instance selection technique based on information retrieval that helps to build domain-specific APE systems, and ii) an optimization procedure to tune the feature weights of the log-linear model that allows the decoder to improve the post-editing quality.
%U https://aclanthology.org/2016.amta-researchers.1
%P 1-15
Markdown (Informal)
[Instance Selection for Online Automatic Post-Editing in a multi-domain scenario](https://aclanthology.org/2016.amta-researchers.1) (Chatterjee et al., AMTA 2016)
ACL