@inproceedings{ghader-monz-2016-words,
title = "Which Words Matter in Defining Phrase Reordering Behavior in Statistical Machine Translation?",
author = "Ghader, Hamidreza and
Monz, Christof",
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.12",
pages = "149--162",
abstract = "Lexicalized and hierarchical reordering models use relative frequencies of fully lexicalized phrase pairs to learn phrase reordering distributions. This results in unreliable estimation for infrequent phrase pairs which also tend to be longer phrases. There are some smoothing techniques used to smooth the distributions in these models. But these techniques are unable to address the similarities between phrase pairs and their reordering distributions. We propose two models to use shorter sub-phrase pairs of an original phrase pair to smooth the phrase reordering distributions. In the first model we follow the classic idea of backing off to shorter histories commonly used in language model smoothing. In the second model, we use syntactic dependencies to identify the most relevant words in a phrase to back off to. We show how these models can be easily applied to existing lexicalized and hierarchical reordering models. Our models achieve improvements of up to 0.40 BLEU points in Chinese-English translation compared to a baseline which uses a regular lexicalized reordering model and a hierarchical reordering model. The results show that not all the words inside a phrase pair are equally important in defining phrase reordering behavior and shortening towards important words will decrease the sparsity problem for long phrase pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghader-monz-2016-words">
<titleInfo>
<title>Which Words Matter in Defining Phrase Reordering Behavior in Statistical Machine Translation?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamidreza</namePart>
<namePart type="family">Ghader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</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>Lexicalized and hierarchical reordering models use relative frequencies of fully lexicalized phrase pairs to learn phrase reordering distributions. This results in unreliable estimation for infrequent phrase pairs which also tend to be longer phrases. There are some smoothing techniques used to smooth the distributions in these models. But these techniques are unable to address the similarities between phrase pairs and their reordering distributions. We propose two models to use shorter sub-phrase pairs of an original phrase pair to smooth the phrase reordering distributions. In the first model we follow the classic idea of backing off to shorter histories commonly used in language model smoothing. In the second model, we use syntactic dependencies to identify the most relevant words in a phrase to back off to. We show how these models can be easily applied to existing lexicalized and hierarchical reordering models. Our models achieve improvements of up to 0.40 BLEU points in Chinese-English translation compared to a baseline which uses a regular lexicalized reordering model and a hierarchical reordering model. The results show that not all the words inside a phrase pair are equally important in defining phrase reordering behavior and shortening towards important words will decrease the sparsity problem for long phrase pairs.</abstract>
<identifier type="citekey">ghader-monz-2016-words</identifier>
<location>
<url>https://aclanthology.org/2016.amta-researchers.12</url>
</location>
<part>
<date>2016-oct 28 - nov 1</date>
<extent unit="page">
<start>149</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Which Words Matter in Defining Phrase Reordering Behavior in Statistical Machine Translation?
%A Ghader, Hamidreza
%A Monz, Christof
%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 ghader-monz-2016-words
%X Lexicalized and hierarchical reordering models use relative frequencies of fully lexicalized phrase pairs to learn phrase reordering distributions. This results in unreliable estimation for infrequent phrase pairs which also tend to be longer phrases. There are some smoothing techniques used to smooth the distributions in these models. But these techniques are unable to address the similarities between phrase pairs and their reordering distributions. We propose two models to use shorter sub-phrase pairs of an original phrase pair to smooth the phrase reordering distributions. In the first model we follow the classic idea of backing off to shorter histories commonly used in language model smoothing. In the second model, we use syntactic dependencies to identify the most relevant words in a phrase to back off to. We show how these models can be easily applied to existing lexicalized and hierarchical reordering models. Our models achieve improvements of up to 0.40 BLEU points in Chinese-English translation compared to a baseline which uses a regular lexicalized reordering model and a hierarchical reordering model. The results show that not all the words inside a phrase pair are equally important in defining phrase reordering behavior and shortening towards important words will decrease the sparsity problem for long phrase pairs.
%U https://aclanthology.org/2016.amta-researchers.12
%P 149-162
Markdown (Informal)
[Which Words Matter in Defining Phrase Reordering Behavior in Statistical Machine Translation?](https://aclanthology.org/2016.amta-researchers.12) (Ghader & Monz, AMTA 2016)
ACL