@inproceedings{ortiz-martinez-etal-2005-thot,
title = "Thot: a Toolkit To Train Phrase-based Statistical Translation Models",
author = "Ortiz-Mart{\'\i}nez, Daniel and
Garc{\'\i}a-Varea, Ismael and
Casacuberta, Francisco",
booktitle = "Proceedings of Machine Translation Summit X: Papers",
month = sep # " 13-15",
year = "2005",
address = "Phuket, Thailand",
url = "https://aclanthology.org/2005.mtsummit-papers.19",
pages = "141--148",
abstract = "In this paper, we present the Thot toolkit, a set of tools to train phrase-based models for statistical machine translation, which is publicly available as open source software. The toolkit obtains phrase-based models from word-based alignment models; to our knowledge, this functionality has not been offered by any publicly available toolkit. The Thot toolkit also implements a new way for estimating phrase models, this allows to obtain more complete phrase models than the methods described in the literature, including a segmentation length submodel. The toolkit output can be given in different formats in order to be used by other statistical machine translation tools like Pharaoh, which is a beam search decoder for phrase-based alignment models which was used in order to perform translation experiments with the generated models. Additionally, the Thot toolkit can be used to obtain the best alignment between a sentence pair at phrase level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ortiz-martinez-etal-2005-thot">
<titleInfo>
<title>Thot: a Toolkit To Train Phrase-based Statistical Translation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Ortiz-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismael</namePart>
<namePart type="family">García-Varea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Casacuberta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2005-sep 13-15</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit X: Papers</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Phuket, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the Thot toolkit, a set of tools to train phrase-based models for statistical machine translation, which is publicly available as open source software. The toolkit obtains phrase-based models from word-based alignment models; to our knowledge, this functionality has not been offered by any publicly available toolkit. The Thot toolkit also implements a new way for estimating phrase models, this allows to obtain more complete phrase models than the methods described in the literature, including a segmentation length submodel. The toolkit output can be given in different formats in order to be used by other statistical machine translation tools like Pharaoh, which is a beam search decoder for phrase-based alignment models which was used in order to perform translation experiments with the generated models. Additionally, the Thot toolkit can be used to obtain the best alignment between a sentence pair at phrase level.</abstract>
<identifier type="citekey">ortiz-martinez-etal-2005-thot</identifier>
<location>
<url>https://aclanthology.org/2005.mtsummit-papers.19</url>
</location>
<part>
<date>2005-sep 13-15</date>
<extent unit="page">
<start>141</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thot: a Toolkit To Train Phrase-based Statistical Translation Models
%A Ortiz-Martínez, Daniel
%A García-Varea, Ismael
%A Casacuberta, Francisco
%S Proceedings of Machine Translation Summit X: Papers
%D 2005
%8 sep 13 15
%C Phuket, Thailand
%F ortiz-martinez-etal-2005-thot
%X In this paper, we present the Thot toolkit, a set of tools to train phrase-based models for statistical machine translation, which is publicly available as open source software. The toolkit obtains phrase-based models from word-based alignment models; to our knowledge, this functionality has not been offered by any publicly available toolkit. The Thot toolkit also implements a new way for estimating phrase models, this allows to obtain more complete phrase models than the methods described in the literature, including a segmentation length submodel. The toolkit output can be given in different formats in order to be used by other statistical machine translation tools like Pharaoh, which is a beam search decoder for phrase-based alignment models which was used in order to perform translation experiments with the generated models. Additionally, the Thot toolkit can be used to obtain the best alignment between a sentence pair at phrase level.
%U https://aclanthology.org/2005.mtsummit-papers.19
%P 141-148
Markdown (Informal)
[Thot: a Toolkit To Train Phrase-based Statistical Translation Models](https://aclanthology.org/2005.mtsummit-papers.19) (Ortiz-Martínez et al., MTSummit 2005)
ACL