National Institute of Information and Communications Technology, Incorporated

Atsushi Fujita

Eiichiro Sumita

Kenji Imamura

Benjamin Marie

Provided is a pseudo parallel translation data generation apparatus for generating pseudo parallel translation data for accurately performing machine translation in an adaptation target domain even when there exists no parallel translation data for the adaptation target domain. Using other-domains parallel translation data D(L-L), other-domains first language data D(L), other-domains second language D(L), adaptation target domain first language data D(R), and adaptation target domain second language data D(R), the pseudo parallel translation data generation apparatusperforms optimization processing for a cross-lingual language model including an input data embedding unitand an XLM processing unit, and performs parameter optimization processing for a pseudo parallel translation data generation NMT model including the input data embedding unit after the optimization processing and a machine translation processing unit. Performing processing using the pseudo parallel translation data generation machine translation model obtained by the parameter optimization processing allows for obtaining pseudo parallel translation data for the adaptation target domain for which no parallel translation data sets exist.

Method for training machine translation model for generating pseudo parallel translation data, method for obtaining pseudo parallel translation data, and method for training machine translation model

Provided are a model training method for neural machine translation that enhances an encoder using a monolingual corpus of a target language and improves the accuracy of the entire translator, and a machine translation system for performing the model training method. The machine translation systemuses a monolingual corpus of the target language to obtain multiple pieces of pseudo source language data, thus allowing for obtaining a large amount of pseudo parallel corpus data having diversity. Further, the machine translation systemuses both the pseudo parallel corpus data having diversity, which has been obtained in large quantities, and the base parallel corpus data in a small quantity but with high accuracy, with the applied learning rates changed accordingly, to perform the learning process (training process) for the machine translation model. This allows the machine translation systemto obtain a learned model (machine translation model) with very high accuracy.

Pseudo parallel translation data generation apparatus, machine translation processing apparatus, and pseudo parallel translation data generation method

Growing community of inventors

Koganei, Japan

Atsushi Fujita