@inproceedings{habash-dorr-2002-handling,
title = "Handling translation divergences: combining statistical and symbolic techniques in generation-heavy machine translation",
author = "Habash, Nizar and
Dorr, Bonnie",
editor = "Richardson, Stephen D.",
booktitle = "Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = oct # " 8-12",
year = "2002",
address = "Tiburon, USA",
publisher = "Springer",
url = "https://link.springer.com/chapter/10.1007/3-540-45820-4_9",
pages = "84--93",
abstract = "This paper describes a novel approach to handling translation divergences in a Generation-Heavy Hybrid Machine Translation (GHMT) system. The translation divergence problem is usually reserved for Transfer and Interlingual MT because it requires a large combination of complex lexical and structural mappings. A major requirement of these approaches is the accessibility of large amounts of explicit symmetric knowledge for both source and target languages. This limitation renders Transfer and Interlingual approaches ineffective in the face of structurally-divergent language pairs with asymmetric resources. GHMT addresses the more common form of this problem, source-poor/targetrich, by fully exploiting symbolic and statistical target-language resources. This non-interlingual non-transfer approach is accomplished by using target-language lexical semantics, categorial variations and subcategorization frames to overgenerate multiple lexico-structural variations from a target-glossed syntactic dependency of the source-language sentence. The symbolic overgeneration, which accounts for different possible translation divergences, is constrained by a statistical target-language model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="habash-dorr-2002-handling">
<titleInfo>
<title>Handling translation divergences: combining statistical and symbolic techniques in generation-heavy machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Dorr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2002-oct 8-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Tiburon, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a novel approach to handling translation divergences in a Generation-Heavy Hybrid Machine Translation (GHMT) system. The translation divergence problem is usually reserved for Transfer and Interlingual MT because it requires a large combination of complex lexical and structural mappings. A major requirement of these approaches is the accessibility of large amounts of explicit symmetric knowledge for both source and target languages. This limitation renders Transfer and Interlingual approaches ineffective in the face of structurally-divergent language pairs with asymmetric resources. GHMT addresses the more common form of this problem, source-poor/targetrich, by fully exploiting symbolic and statistical target-language resources. This non-interlingual non-transfer approach is accomplished by using target-language lexical semantics, categorial variations and subcategorization frames to overgenerate multiple lexico-structural variations from a target-glossed syntactic dependency of the source-language sentence. The symbolic overgeneration, which accounts for different possible translation divergences, is constrained by a statistical target-language model.</abstract>
<identifier type="citekey">habash-dorr-2002-handling</identifier>
<location>
<url>https://link.springer.com/chapter/10.1007/3-540-45820-4_9</url>
</location>
<part>
<date>2002-oct 8-12</date>
<extent unit="page">
<start>84</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Handling translation divergences: combining statistical and symbolic techniques in generation-heavy machine translation
%A Habash, Nizar
%A Dorr, Bonnie
%Y Richardson, Stephen D.
%S Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 2002
%8 oct 8 12
%I Springer
%C Tiburon, USA
%F habash-dorr-2002-handling
%X This paper describes a novel approach to handling translation divergences in a Generation-Heavy Hybrid Machine Translation (GHMT) system. The translation divergence problem is usually reserved for Transfer and Interlingual MT because it requires a large combination of complex lexical and structural mappings. A major requirement of these approaches is the accessibility of large amounts of explicit symmetric knowledge for both source and target languages. This limitation renders Transfer and Interlingual approaches ineffective in the face of structurally-divergent language pairs with asymmetric resources. GHMT addresses the more common form of this problem, source-poor/targetrich, by fully exploiting symbolic and statistical target-language resources. This non-interlingual non-transfer approach is accomplished by using target-language lexical semantics, categorial variations and subcategorization frames to overgenerate multiple lexico-structural variations from a target-glossed syntactic dependency of the source-language sentence. The symbolic overgeneration, which accounts for different possible translation divergences, is constrained by a statistical target-language model.
%U https://link.springer.com/chapter/10.1007/3-540-45820-4_9
%P 84-93
Markdown (Informal)
[Handling translation divergences: combining statistical and symbolic techniques in generation-heavy machine translation](https://link.springer.com/chapter/10.1007/3-540-45820-4_9) (Habash & Dorr, AMTA 2002)
ACL