AUTOMATIC POST-EDITING MODEL FOR GENERATED NATURAL LANGUAGE TEXT

    公开(公告)号:US20240370666A1

    公开(公告)日:2024-11-07

    申请号:US18773129

    申请日:2024-07-15

    Applicant: GOOGLE LLC

    Abstract: 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 automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

    AUTOMATIC POST-EDITING MODEL FOR NEURAL MACHINE TRANSLATION

    公开(公告)号:US20210019373A1

    公开(公告)日:2021-01-21

    申请号:US16511806

    申请日:2019-07-15

    Applicant: Google LLC

    Abstract: 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 automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

    AUTOMATIC POST-EDITING MODEL FOR NEURAL MACHINE TRANSLATION

    公开(公告)号:US20220215183A1

    公开(公告)日:2022-07-07

    申请号:US17700123

    申请日:2022-03-21

    Applicant: GOOGLE LLC

    Abstract: 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 automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

    Automatic post-editing model for neural machine translation

    公开(公告)号:US11295092B2

    公开(公告)日:2022-04-05

    申请号:US16511806

    申请日:2019-07-15

    Applicant: Google LLC

    Abstract: 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 automatic post-editing model can be trained using automatically generated training instances. A training instance is automatically generated by processing text in a first language using a neural machine translation model to generate text in a second language. The text in the second language is processed using a neural machine translation model to generate training text in the first language. A training instance can include the text in the first language as well as the training text in the first language.

Patent Agency Ranking