<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ambati-lavie-2008-improving">
    <titleInfo>
        <title>Improving Syntax-Driven Translation Models by Re-structuring Divergent and Nonisomorphic Parse Tree Structures</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vamshi</namePart>
        <namePart type="family">Ambati</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alon</namePart>
        <namePart type="family">Lavie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2008-oct 21-25</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Student Research Workshop</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">Waikiki, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Syntax-based approaches to statistical MT require syntax-aware methods for acquiring their underlying translation models from parallel data. This acquisition process can be driven by syntactic trees for either the source or target language, or by trees on both sides. Work to date has demonstrated that using trees for both sides suffers from severe coverage problems. This is primarily due to the highly restrictive space of constituent segmentations that the trees on two sides introduce, which adversely affects the recall of the resulting translation models. Approaches that project from trees on one side, on the other hand, have higher levels of recall, but suffer from lower precision, due to the lack of syntactically-aware word alignments. In this paper we explore the issue of lexical coverage of the translation models learned in both of these scenarios. We specifically look at how the non-isomorphic nature of the parse trees for the two languages affects recall and coverage. We then propose a novel technique for restructuring target parse trees, that generates highly isomorphic target trees that preserve the syntactic boundaries of constituents that were aligned in the original parse trees. We evaluate the translation models learned from these restructured trees and show that they are significantly better than those learned using trees on both sides and trees on one side.</abstract>
    <identifier type="citekey">ambati-lavie-2008-improving</identifier>
    <location>
        <url>https://aclanthology.org/2008.amta-srw.1</url>
    </location>
    <part>
        <date>2008-oct 21-25</date>
        <extent unit="page">
            <start>235</start>
            <end>244</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Syntax-Driven Translation Models by Re-structuring Divergent and Nonisomorphic Parse Tree Structures
%A Ambati, Vamshi
%A Lavie, Alon
%S Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Student Research Workshop
%D 2008
%8 oct 21 25
%I Association for Machine Translation in the Americas
%C Waikiki, USA
%F ambati-lavie-2008-improving
%X Syntax-based approaches to statistical MT require syntax-aware methods for acquiring their underlying translation models from parallel data. This acquisition process can be driven by syntactic trees for either the source or target language, or by trees on both sides. Work to date has demonstrated that using trees for both sides suffers from severe coverage problems. This is primarily due to the highly restrictive space of constituent segmentations that the trees on two sides introduce, which adversely affects the recall of the resulting translation models. Approaches that project from trees on one side, on the other hand, have higher levels of recall, but suffer from lower precision, due to the lack of syntactically-aware word alignments. In this paper we explore the issue of lexical coverage of the translation models learned in both of these scenarios. We specifically look at how the non-isomorphic nature of the parse trees for the two languages affects recall and coverage. We then propose a novel technique for restructuring target parse trees, that generates highly isomorphic target trees that preserve the syntactic boundaries of constituents that were aligned in the original parse trees. We evaluate the translation models learned from these restructured trees and show that they are significantly better than those learned using trees on both sides and trees on one side.
%U https://aclanthology.org/2008.amta-srw.1
%P 235-244

Markdown (Informal)

[Improving Syntax-Driven Translation Models by Re-structuring Divergent and Nonisomorphic Parse Tree Structures](https://aclanthology.org/2008.amta-srw.1) (Ambati & Lavie, AMTA 2008)

• Improving Syntax-Driven Translation Models by Re-structuring Divergent and Nonisomorphic Parse Tree Structures (Ambati & Lavie, AMTA 2008)

ACL

• Vamshi Ambati and Alon Lavie. 2008. Improving Syntax-Driven Translation Models by Re-structuring Divergent and Nonisomorphic Parse Tree Structures. In Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Student Research Workshop, pages 235–244, Waikiki, USA. Association for Machine Translation in the Americas.