@inproceedings{hu-etal-2018-contextual,
title = "Contextual Encoding for Translation Quality Estimation",
author = "Hu, Junjie and
Chang, Wei-Cheng and
Wu, Yuexin and
Neubig, Graham",
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/W18-6462",
doi = "10.18653/v1/W18-6462",
pages = "788--793",
abstract = "The task of word-level quality estimation (QE) consists of taking a source sentence and machine-generated translation, and predicting which words in the output are correct and which are wrong. In this paper, propose a method to effectively encode the local and global contextual information for each target word using a three-part neural network approach. The first part uses an embedding layer to represent words and their part-of-speech tags in both languages. The second part leverages a one-dimensional convolution layer to integrate local context information for each target word. The third part applies a stack of feed-forward and recurrent neural networks to further encode the global context in the sentence before making the predictions. This model was submitted as the CMU entry to the WMT2018 shared task on QE, and achieves strong results, ranking first in three of the six tracks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2018-contextual">
<titleInfo>
<title>Contextual Encoding for Translation Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Cheng</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuexin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</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>The task of word-level quality estimation (QE) consists of taking a source sentence and machine-generated translation, and predicting which words in the output are correct and which are wrong. In this paper, propose a method to effectively encode the local and global contextual information for each target word using a three-part neural network approach. The first part uses an embedding layer to represent words and their part-of-speech tags in both languages. The second part leverages a one-dimensional convolution layer to integrate local context information for each target word. The third part applies a stack of feed-forward and recurrent neural networks to further encode the global context in the sentence before making the predictions. This model was submitted as the CMU entry to the WMT2018 shared task on QE, and achieves strong results, ranking first in three of the six tracks.</abstract>
<identifier type="citekey">hu-etal-2018-contextual</identifier>
<identifier type="doi">10.18653/v1/W18-6462</identifier>
<location>
<url>https://aclanthology.org/W18-6462</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>788</start>
<end>793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextual Encoding for Translation Quality Estimation
%A Hu, Junjie
%A Chang, Wei-Cheng
%A Wu, Yuexin
%A Neubig, Graham
%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 hu-etal-2018-contextual
%X The task of word-level quality estimation (QE) consists of taking a source sentence and machine-generated translation, and predicting which words in the output are correct and which are wrong. In this paper, propose a method to effectively encode the local and global contextual information for each target word using a three-part neural network approach. The first part uses an embedding layer to represent words and their part-of-speech tags in both languages. The second part leverages a one-dimensional convolution layer to integrate local context information for each target word. The third part applies a stack of feed-forward and recurrent neural networks to further encode the global context in the sentence before making the predictions. This model was submitted as the CMU entry to the WMT2018 shared task on QE, and achieves strong results, ranking first in three of the six tracks.
%R 10.18653/v1/W18-6462
%U https://aclanthology.org/W18-6462
%U https://doi.org/10.18653/v1/W18-6462
%P 788-793
Markdown (Informal)
[Contextual Encoding for Translation Quality Estimation](https://aclanthology.org/W18-6462) (Hu et al., 2018)
ACL
- Junjie Hu, Wei-Cheng Chang, Yuexin Wu, and Graham Neubig. 2018. Contextual Encoding for Translation Quality Estimation. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 788–793, Belgium, Brussels. Association for Computational Linguistics.