Automatic Rule Learning for Resource-Limited MT

Authors:
Jaime G. Carbonell;Katharina Probst;Erik Peterson;Christian Monson;Alon Lavie;Ralf D. Brown;Lori S. Levin
Affiliations:
-;-;-;-;-;-;-
Venue:
AMTA '02 Proceedings of the 5th Conference of the Association for Machine Translation in the Americas on Machine Translation: From Research to Real Users
Year:
2002

Citing 1
Cited 8

Theoretical underpinnings of version spaces

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2

Mood and modality: out of theory and into the fray

Natural Language Engineering
Rapid porting of DUSTer to Hindi

ACM Transactions on Asian Language Information Processing (TALIP)
A probability model to improve word alignment

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Using 'smart' bilingual projection to feature-tag a monolingual dictionary

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Automatic induction of bilingual resources from aligned parallel corpora: application to shallow-transfer machine translation

Machine Translation
On the Automatic Learning of Bilingual Resources: Some Relevant Factors for Machine Translation

SBIA '08 Proceedings of the 19th Brazilian Symposium on Artificial Intelligence: Advances in Artificial Intelligence
Unsupervised induction of natural language morphology inflection classes

SIGMorPhon '04 Proceedings of the 7th Meeting of the ACL Special Interest Group in Computational Phonology: Current Themes in Computational Phonology and Morphology
Inductive detection of language features via clustering minimal pairs: toward feature-rich grammars in machine translation

SSST '08 Proceedings of the Second Workshop on Syntax and Structure in Statistical Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Machine Translation of minority languages presents unique challenges, including the paucity of bilingual training data and the unavailability of linguistically-trained speakers. This paper focuses on a machine learning approach to transfer-based MT, where data in the form of translations and lexical alignments are elicited from bilingual speakers, and a seeded version-space learning algorithm formulates and refines transfer rules. A rule-generalization lattice is defined based on LFG-style f-structures, permitting generalization operators in the search for the most general rules consistent with the elicited data. The paper presents these methods and illustrates examples.