Automatic rule learning for resource-limited MT

Jaime Carbonell, Katharina Probst, Erik Peterson, Christian Monson, Alon Lavie, Ralf Brown, Lori Levin


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.
Anthology ID:
2002.amta-papers.1
Volume:
Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers
Month:
October 8-12
Year:
2002
Address:
Tiburon, USA
Editor:
Stephen D. Richardson
Venue:
AMTA
SIG:
Publisher:
Springer
Note:
Pages:
1–10
Language:
URL:
https://link.springer.com/chapter/10.1007/3-540-45820-4_1
DOI:
Bibkey:
Cite (ACL):
Jaime Carbonell, Katharina Probst, Erik Peterson, Christian Monson, Alon Lavie, Ralf Brown, and Lori Levin. 2002. Automatic rule learning for resource-limited MT. In Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 1–10, Tiburon, USA. Springer.
Cite (Informal):
Automatic rule learning for resource-limited MT (Carbonell et al., AMTA 2002)
Copy Citation:
PDF:
https://link.springer.com/chapter/10.1007/3-540-45820-4_1