Improving Word Alignment Using Alignment of Deep Structures
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F09%3A00206909" target="_blank" >RIV/00216208:11320/09:00206909 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Improving Word Alignment Using Alignment of Deep Structures
Original language description
In this paper, we describe differences between a classical word alignment on the surface (word-layer alignment) and an alignment of deep syntactic sentence representations (tectogrammatical alignment). The deep structures we use are dependency trees containing content (autosemantic) words as their nodes. Most of other functional words, such as prepositions, articles, and auxiliary verbs are hidden. We introduce an algorithm which aligns such trees using perceptron-based scoring function. For evaluationpurposes, a set of parallel sentences was manually aligned. We show that using statistical word alignment (GIZA ) can improve the tectogrammatical alignment. Surprisingly, we also show that the tectogrammatical alignment can be then used to significantlyimprove the original word alignment.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
AI - Linguistics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/1ET101120503" target="_blank" >1ET101120503: Integration of language resources for information extraction from natural texts</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2009
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 12th International Conference, TSD 2009
ISBN
—
ISSN
0302-9743
e-ISSN
—
Number of pages
8
Pages from-to
—
Publisher name
Springer Verlag
Place of publication
Berlin / Heidelberg
Event location
Berlin / Heidelberg
Event date
Jan 1, 2009
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000270445700009