@inproceedings{sammer-etal-2006-ambiguity,
title = "Ambiguity Reduction for Machine Translation: Human-Computer Collaboration",
author = "Sammer, Marcus and
Reiter, Kobi and
Soderland, Stephen and
Kirchhoff, Katrin and
Etzioni, Oren",
booktitle = "Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = aug # " 8-12",
year = "2006",
address = "Cambridge, Massachusetts, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2006.amta-papers.22",
pages = "193--202",
abstract = "Statistical Machine Translation (SMT) accuracy degrades when there is only a limited amount of training, or when the training is not from the same domain or genre of text as the target application. However, cross-domain applications are typical of many real world tasks. We demonstrate that SMT accuracy can be improved in a cross-domain application by using a controlled language (CL) interface to help reduce lexical ambiguity in the input text. Our system, CL-MT, presents a monolingual user with a choice of word senses for each content word in the input text. CL-MT temporarily adjusts the underlying SMT system's phrase table, boosting the scores of translations that include the word senses preferred by the user and lowering scores for disfavored translations. We demonstrate that this improves translation adequacy in 33.8{\%} of the sentences in Spanish to English translation of news stories, where the SMT system was trained on proceedings of the European Parliament.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sammer-etal-2006-ambiguity">
<titleInfo>
<title>Ambiguity Reduction for Machine Translation: Human-Computer Collaboration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Sammer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kobi</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Soderland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Kirchhoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="family">Etzioni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-aug" 8-12"</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Cambridge, Massachusetts, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Statistical Machine Translation (SMT) accuracy degrades when there is only a limited amount of training, or when the training is not from the same domain or genre of text as the target application. However, cross-domain applications are typical of many real world tasks. We demonstrate that SMT accuracy can be improved in a cross-domain application by using a controlled language (CL) interface to help reduce lexical ambiguity in the input text. Our system, CL-MT, presents a monolingual user with a choice of word senses for each content word in the input text. CL-MT temporarily adjusts the underlying SMT system’s phrase table, boosting the scores of translations that include the word senses preferred by the user and lowering scores for disfavored translations. We demonstrate that this improves translation adequacy in 33.8% of the sentences in Spanish to English translation of news stories, where the SMT system was trained on proceedings of the European Parliament.</abstract>
<identifier type="citekey">sammer-etal-2006-ambiguity</identifier>
<location>
<url>https://aclanthology.org/2006.amta-papers.22</url>
</location>
<part>
<date>2006-aug" 8-12"</date>
<extent unit="page">
<start>193</start>
<end>202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ambiguity Reduction for Machine Translation: Human-Computer Collaboration
%A Sammer, Marcus
%A Reiter, Kobi
%A Soderland, Stephen
%A Kirchhoff, Katrin
%A Etzioni, Oren
%S Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 2006
%8 aug" 8 12"
%I Association for Machine Translation in the Americas
%C Cambridge, Massachusetts, USA
%F sammer-etal-2006-ambiguity
%X Statistical Machine Translation (SMT) accuracy degrades when there is only a limited amount of training, or when the training is not from the same domain or genre of text as the target application. However, cross-domain applications are typical of many real world tasks. We demonstrate that SMT accuracy can be improved in a cross-domain application by using a controlled language (CL) interface to help reduce lexical ambiguity in the input text. Our system, CL-MT, presents a monolingual user with a choice of word senses for each content word in the input text. CL-MT temporarily adjusts the underlying SMT system’s phrase table, boosting the scores of translations that include the word senses preferred by the user and lowering scores for disfavored translations. We demonstrate that this improves translation adequacy in 33.8% of the sentences in Spanish to English translation of news stories, where the SMT system was trained on proceedings of the European Parliament.
%U https://aclanthology.org/2006.amta-papers.22
%P 193-202
Markdown (Informal)
[Ambiguity Reduction for Machine Translation: Human-Computer Collaboration](https://aclanthology.org/2006.amta-papers.22) (Sammer et al., AMTA 2006)
ACL
- Marcus Sammer, Kobi Reiter, Stephen Soderland, Katrin Kirchhoff, and Oren Etzioni. 2006. Ambiguity Reduction for Machine Translation: Human-Computer Collaboration. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 193–202, Cambridge, Massachusetts, USA. Association for Machine Translation in the Americas.