Method and apparatus for automatic construction of...

Data processing: speech signal processing – linguistics – language – Linguistics – Translation machine

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C704S002000

Reexamination Certificate

active

06195631

ABSTRACT:

BACKGROUND OF THE INVENTION
1. Field of Invention
The invention relates to automatic language translation. In particular, the invention relates to a method and apparatus for training language translation systems automatically from bilingual data.
2. Description of Related Art
Language translation systems have existed for several years. These systems typically require a large hand-coding effort to construct translation lexicons and rule sets. This type of manual coding is expensive in terms of time and the level of expertise required. A number of approaches have been proposed for automatically learning translation models from examples provided by human translators. However, the types of models created suffer from a number of problems, such as low translation quality or a requirement for very large amounts of training data.
SUMMARY OF THE INVENTION
A method and apparatus for automatically constructing hierarchical transduction models for language translation is presented. The input to the construction process may be a database of examples each consisting of a transcribed speech utterance and its translation into another language. A translation pairing score is assigned (or computed) for translating a word in the source language into each of the possible translations it has in the target language. For each instance of the resulting training dataset, a head transducer may be constructed that translates the source string into the target string by splitting the source string into a source head word, the words preceding the source head word, and the words following the source head word. This process may be performed recursively to generate a set of transducer fragments. The transducer fragments may form a statistical head transducer model. The head transducer translation model may then be input into a transduction search module.
These and other features and advantages of this invention are described or apparent from the following detailed description of the preferred embodiments.


REFERENCES:
patent: 4868750 (1989-09-01), Kucera et al.
patent: 5510981 (1996-04-01), Berger et al.
patent: 5768603 (1998-06-01), Brown et al.
patent: 5805832 (1998-09-01), Brown et al.
patent: 5815196 (1998-09-01), Alshawi
patent: 5867811 (1999-02-01), O'Donoghue
patent: 5870706 (1999-02-01), Alshawi
Alshawi, H. et al., “Head Automata and Bilingual Tiling: Translation with Minimal Representations”. In Proceeding of the 34 th Annual Meeting of the Association for Computational Linguistics, Santa Crux, CA 1996. pp. 1-17.
Alshawi, H. et al., “A Comparison of Head Transducers and Transfer for a Limited Domain Translation Application”. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics. Madrid. Jun. 1997.
Alshawi, H. et al., “State Transition Cost Functions and an Application to Language Translation”. IEEE 1997.
Alshawi, H. “Head Automata for Speech Translation” Proc. Fourth International Conference on Spoken Language Processing, Philadelphia, Pennsylvanis, 1996.
Gale, W., et al., “Identifying Word Correspondences in parallel Texts” Computational Linguistics, 1992.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Method and apparatus for automatic construction of... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for automatic construction of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for automatic construction of... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2593958

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.