A Computer-Implemented Method of Creating a Translation Model for Low Resource Language Pairs and a Machine Translation System using this Translation Model

Patent №

US 11,037,028

Granted

2021-06-15

Filed 2018

Owner

CHARLES UNIVERSITY FACULTY OF MATHEMATICS AND PHYSICS

Lab

AI components

5

ml · nlp · speech · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16237414

A computer-implemented method for creating a translation model for low resource language pairs and applicable on noisy inputs utilizing several approaches: choosing particular input corpora covering in-domain noisy and clean texts as well as unrelated but larger general parallel texts, performing several chosen methods of creating synthetic parallel corpora and filtering, pre-processing, deduplicating and concatenating training corpora.

Machine learningNatural languageSpeechKnowledge representationAI hardwareG06F 40/51G06F 18/2148G06F 40/45G06F 40/58G06N 3/02G06N 3/044G06N 3/0442G06N 3/045+4 more

AI classification

Natural language1.00
Speech1.00
Machine learning1.00
AI hardware0.84
Knowledge representation0.72
Vision0.02
Planning0.00
Evolutionary computation0.00

Ownership

CHARLES UNIVERSITY FACULTY OF MATHEMATICS AND PHYSICS

assignment · 482440753

Assignors

BOJAR, ONDREJ, SUDARIKOV, ROMAN

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC