Shalt2: a symmetric machine translation system with conceptual transfer

Authors:
Koichi Takeda;Tetsuya Nasukawa;Naohiko Uramoto;Taijiro Tsutsumi
Affiliations:
Tokyo Research Laboratory, IBM Research, Tokyo, Japan;Tokyo Research Laboratory, IBM Research, Tokyo, Japan;Tokyo Research Laboratory, IBM Research, Tokyo, Japan;Tokyo Research Laboratory, IBM Research, Tokyo, Japan
Venue:
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 3
Year:
1992

Citing 7
Cited 2

Semantic-head-driven generation

Computational Linguistics
Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems
Designing Natural Language Objects

Proceedings of the Second International Symposium on Database Systems for Advanced Applications
Structural disambiguation with constraint propagation

ACL '90 Proceedings of the 28th annual meeting on Association for Computational Linguistics
A prototype English-Japanese machine translation system for translating IBM computer manuals

COLING '86 Proceedings of the 11th coference on Computational linguistics
Generation as structure driven derivation

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
Dependency Analyzer: a knowledge-based approach to structural disambiguation

COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 2

Robust method of pronoun resolution using full-text information

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Full-text processing: improving a practical NLP system based on surface information within the context

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shalt2 is a knowledge-based machine translation system with a symmetric architecture. The grammar rules, mapping rules between syntactic and conceptual (semantic) representations, and transfer rules for conceptual paraphrasing are all bi-directional knowledge sources used by both a parser and a generator.