@inproceedings{henriquez-etal-2010-upc,
title = "{UPC}-{BMIC}-{VDU} system description for the {IWSLT} 2010: testing several collocation segmentations in a phrase-based {SMT} system",
author = "Henr{\'\i}quez, Carlos and
Costa-juss{\`a}, Marta R. and
Daudaravicius, Vidas and
Banchs, Rafael E. and
Mari{\~n}o, Jos{\'e} B.",
booktitle = "Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign",
month = dec # " 2-3",
year = "2010",
address = "Paris, France",
url = "https://aclanthology.org/2010.iwslt-evaluation.26",
pages = "189--195",
abstract = "This paper describes the UPC-BMIC-VMU participation in the IWSLT 2010 evaluation campaign. The SMT system is a standard phrase-based enriched with novel segmentations. These novel segmentations are computed using statistical measures such as Log-likelihood, T-score, Chi-squared, Dice, Mutual Information or Gravity-Counts. The analysis of translation results allows to divide measures into three groups. First, Log-likelihood, Chi-squared and T-score tend to combine high frequency words and collocation segments are very short. They improve the SMT system by adding new translation units. Second, Mutual Information and Dice tend to combine low frequency words and collocation segments are short. They improve the SMT system by smoothing the translation units. And third, GravityCounts tends to combine high and low frequency words and collocation segments are long. However, in this case, the SMT system is not improved. Thus, the road-map for translation system improvement is to introduce new phrases with either low frequency or high frequency words. It is hard to introduce new phrases with low and high frequency words in order to improve translation quality. Experimental results are reported in the French-to-English IWSLT 2010 evaluation where our system was ranked 3rd out of nine systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="henriquez-etal-2010-upc">
<titleInfo>
<title>UPC-BMIC-VDU system description for the IWSLT 2010: testing several collocation segmentations in a phrase-based SMT system</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Henríquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidas</namePart>
<namePart type="family">Daudaravicius</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Banchs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Mariño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-dec 2-3</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Paris, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the UPC-BMIC-VMU participation in the IWSLT 2010 evaluation campaign. The SMT system is a standard phrase-based enriched with novel segmentations. These novel segmentations are computed using statistical measures such as Log-likelihood, T-score, Chi-squared, Dice, Mutual Information or Gravity-Counts. The analysis of translation results allows to divide measures into three groups. First, Log-likelihood, Chi-squared and T-score tend to combine high frequency words and collocation segments are very short. They improve the SMT system by adding new translation units. Second, Mutual Information and Dice tend to combine low frequency words and collocation segments are short. They improve the SMT system by smoothing the translation units. And third, GravityCounts tends to combine high and low frequency words and collocation segments are long. However, in this case, the SMT system is not improved. Thus, the road-map for translation system improvement is to introduce new phrases with either low frequency or high frequency words. It is hard to introduce new phrases with low and high frequency words in order to improve translation quality. Experimental results are reported in the French-to-English IWSLT 2010 evaluation where our system was ranked 3rd out of nine systems.</abstract>
<identifier type="citekey">henriquez-etal-2010-upc</identifier>
<location>
<url>https://aclanthology.org/2010.iwslt-evaluation.26</url>
</location>
<part>
<date>2010-dec 2-3</date>
<extent unit="page">
<start>189</start>
<end>195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UPC-BMIC-VDU system description for the IWSLT 2010: testing several collocation segmentations in a phrase-based SMT system
%A Henríquez, Carlos
%A Costa-jussà, Marta R.
%A Daudaravicius, Vidas
%A Banchs, Rafael E.
%A Mariño, José B.
%S Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign
%D 2010
%8 dec 2 3
%C Paris, France
%F henriquez-etal-2010-upc
%X This paper describes the UPC-BMIC-VMU participation in the IWSLT 2010 evaluation campaign. The SMT system is a standard phrase-based enriched with novel segmentations. These novel segmentations are computed using statistical measures such as Log-likelihood, T-score, Chi-squared, Dice, Mutual Information or Gravity-Counts. The analysis of translation results allows to divide measures into three groups. First, Log-likelihood, Chi-squared and T-score tend to combine high frequency words and collocation segments are very short. They improve the SMT system by adding new translation units. Second, Mutual Information and Dice tend to combine low frequency words and collocation segments are short. They improve the SMT system by smoothing the translation units. And third, GravityCounts tends to combine high and low frequency words and collocation segments are long. However, in this case, the SMT system is not improved. Thus, the road-map for translation system improvement is to introduce new phrases with either low frequency or high frequency words. It is hard to introduce new phrases with low and high frequency words in order to improve translation quality. Experimental results are reported in the French-to-English IWSLT 2010 evaluation where our system was ranked 3rd out of nine systems.
%U https://aclanthology.org/2010.iwslt-evaluation.26
%P 189-195
Markdown (Informal)
[UPC-BMIC-VDU system description for the IWSLT 2010: testing several collocation segmentations in a phrase-based SMT system](https://aclanthology.org/2010.iwslt-evaluation.26) (Henríquez et al., IWSLT 2010)
ACL