-
公开(公告)号：CA2068780C
公开(公告)日：1998-12-22
申请号：CA2068780
申请日：1992-05-15
Applicant: IBM
Inventor： BROWN PETER F , COCKE JOHN , DELLA PIETRA STEPHEN A , DELLA PIETRA VINCENT J , JELINEK FREDERICK , LAI JENNIFER C , MERCER ROBERT L
Abstract: The present invention is a system for translating text from a first source language into 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 into the target language. The system can either run into 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 states of source transduction, hypothesis generation and target transduction.
-
公开(公告)号：CA2068780A1
公开(公告)日：1993-01-26
申请号：CA2068780
申请日：1992-05-15
Applicant: IBM
-
Search Results
2
records
(took 0.016 seconds)
