Techniques are disclosed for training and/or utilizing an automatic post-editing model in
correcting translation error (s) introduced by a neural machine translation model. The …

An electronic apparatus is disclosed. The electronic apparatus includes: an inputter
comprising input circuitry configured to acquire an input sentence of a first language …

Provided are a system and method for end-to-end neural machine translation. The method
of end-to-end neural machine translation includes performing learning including a READ …

A processor-implemented method includes: using an encoder, determining, for each of a
plurality of tokens included in an input sequence, a self-attention weight based on a token …

This invention relates generally to speech processing and more particularly to end-to-end
automatic speech recognition (ASR) that utilizes long contextual information. Some …

2020-10-27 Assigned to GOOGLE LLC reassignment GOOGLE LLC ASSIGNMENT OF
ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: I, TE …

Asystem for reinforcement learning based controlled natural language generation is
disclosed. The system includes a token generator subsystem to generate an initial output …