Abstract

The present invention is a system for translating text from a first source language into a second target language. The system assigns probabilities or scores to various target-language translations and then displays or makes otherwise available the highest scoring translations. The source text is first transduced into one or more intermediate structural representations. From these intermediate source structures a set of intermediate target-structure hypotheses is generated. These hypotheses are scored by two different models: a language model which assigns a probability or score to an intermediate target structure, and a translation model which assigns a probability or score to the event that an intermediate target structure is translated into an intermediate source structure. Scores from the translation model and language model are combined into a combined score for each intermediate target-structure hypothesis. Finally, a set of target-text hypotheses is produced by transducing the highest scoring target-structure hypotheses into portions of text in the target language. The system can either run in batch mode, in which case it translates source-language text into a target language without human assistance, or it can function as an aid to a human translator. When functioning as an aid to a human translator, the human may simply select from the various translation hypotheses provided by the system, or he may optionally provide hints or constraints on how to perform one or more of the stages of source transduction, hypothesis generation and target transduction.

Other References

• "Method for Inferring Lexical Associations from Textual Co-Occurrences", IBM Technical Disclosure Bulletin, vol. 33 1B, Jun. 1990
• "Tagging Text with a Probabilistic Model", by Bernard Merialdo, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Paris, France, May 14-17, 1991
• "Word-Sense Disambiguation Using Statistical Methods", by Peter F. Brown et al., appearing in the Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, Jun. 1991, pp. 264-270
• "Lex--A Lexical Analyzer Generator", M. E. Lesk, Computer Science Technical Report, No. 39, Bell Laboratories, Oct. 1975
• "Self Organized Language Modeling for Speech Recognition" by F. Jelinek, Language Processing for Speech Recognition, pp. 450-506
• "A Tree-Based Statistical Language Model for Natural Language Speech Recognition" by Lalit R. Bahl et al., IEEE Transactions on Acoustics, vol. 37, No. 7, Jul. 1989, pp. 1001-1008
• "Trainable Grammars for Speech Recognition" by James K. Baker, Speech Communications Papers Presented at the 97th Meeting of the Acoustic Society of America, 1979, pp. 547-550
• "Interpolated Estimation of Markov Source Parameters from Sparse Data" by F. Jelinek and R. L. Mercer, Workshop on Pattern Recognition in Practice, Amsterdam (Netherland): North Holland, May 21-23, 1980
• "An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes", by Leonard E. Baum, Inequalities, vol. 3, 1972, pp. 1-8
• "Aligning Sentences in Parallel Corpora" by Peter F. Brown et al., appearing in the Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, Jun. 1991, pp. 169-176
• "Partial Traceback in Continuous Speech Recognition" by James C. Spohrer et al., Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Paris, France, 1982
• "Deriving Translation Data from Bilingual Texts", Catizone et al., Proceedings of the First International Acquisition Workshop, Detroit, Mich., 1989
• "Making Connections", by M. Kay, appearing in ACH/ALLC '91, Tempe, Ariz., 1991, p.