The technology provides an approach to train translation models that are robust to transcription errors and punctuation errors. The approach includes introducing errors from actual automatic speech recognition and automatic punctuation systems into the source side of the machine translation training data. A method for training a machine translation model includes performing automatic speech recognition on input source audio to generate a system transcript. The method aligns a human transcript of the source audio to the system transcript, including projecting system segmentation onto the human transcript. Then the method performs segment robustness training of a machine translation model according to the aligned human and system transcripts, and performs system robustness training of the machine translation model, e.g., by injecting token errors into training data.

Provided are an interactive machine translation method and apparatus, a device, and a medium. The method includes: acquiring a source statement input by a user; translating the source statement into a first target statement; determining whether the user adjusts a first vocabulary in the first target statement; and in response to determining that the user adjusts the first vocabulary in the first target statement, acquiring a second vocabulary for replacing the first vocabulary, and adjusting, based on the second vocabulary, a vocabulary sequence located in a front of the first vocabulary and a vocabulary sequence located behind the first vocabulary in the first target statement to generate a second target statement.

A specification of a first natural language understanding (NLU) machine learning model for a first human communication language is received. The specification specifies a language content associated with one or more intents of the first NLU machine learning model in the first human communication language. An identification of an association between the first NLU machine learning model and a second NLU machine learning model for a second human communication language is received. The first NLU machine learning model and the second NLU machine learning model are managed together. This includes detecting a change to the first NLU machine learning model in the first human communication language and in response automatically assisting in maintaining consistency in the second NLU machine learning model in the second human communication language with respect to the detected change.

A specification of a first natural language understanding (NLU) machine learning model for a first human communication language is received. The specification specifies a language content associated with one or more intents of the first NLU machine learning model in the first human communication language. An identification of an association between the first NLU machine learning model and a second NLU machine learning model for a second human communication language is received. The first NLU machine learning model and the second NLU machine learning model are managed together. This includes detecting a change to the first NLU machine learning model in the first human communication language and in response automatically assisting in maintaining consistency in the second NLU machine learning model in the second human communication language with respect to the detected change.

A method, a system, and a computer program product for retrieving metadata files using a local metadata index. A request to access one or more metadata files associated with at least one computing component is received. At least one primary key and at least secondary key identifying the computing component are determined. An identifier of a storage location storing the metadata files is associated with the primary key and the secondary key. A metadata index for the metadata files is generated. The metadata index includes the primary key, the secondary key, and the associated identifier of the storage location. The metadata index is stored in a memory location associated with the computing component. The stored metadata index is accessed and the metadata files are retrieved using the stored metadata index.

A method, a system, and a computer program product for retrieving metadata files using a local metadata index. A request to access one or more metadata files associated with at least one computing component is received. At least one primary key and at least secondary key identifying the computing component are determined. An identifier of a storage location storing the metadata files is associated with the primary key and the secondary key. A metadata index for the metadata files is generated. The metadata index includes the primary key, the secondary key, and the associated identifier of the storage location. The metadata index is stored in a memory location associated with the computing component. The stored metadata index is accessed and the metadata files are retrieved using the stored metadata index.

A translation device includes a storage unit configured to store a plurality of pieces of learning data, a normalized sentence learning unit configured to perform learning on the plurality of pieces of learning data by combining original text for learning and a corresponding normalized sentence for learning, a translated sentence learning unit configured to perform learning on the plurality of pieces of learning data by combining the original text for learning and a corresponding translated sentence for learning, and a model generation unit configured to generate one normalization/translation model on the basis of a result of learning by the normalized sentence learning unit and the translated sentence learning unit, in which, on at least a part of the learning data, the translated sentence learning unit performs learning after the normalized sentence learning unit performs learning.

A translation device includes a storage unit configured to store a plurality of pieces of learning data, a normalized sentence learning unit configured to perform learning on the plurality of pieces of learning data by combining original text for learning and a corresponding normalized sentence for learning, a translated sentence learning unit configured to perform learning on the plurality of pieces of learning data by combining the original text for learning and a corresponding translated sentence for learning, and a model generation unit configured to generate one normalization/translation model on the basis of a result of learning by the normalized sentence learning unit and the translated sentence learning unit, in which, on at least a part of the learning data, the translated sentence learning unit performs learning after the normalized sentence learning unit performs learning.

According to an aspect, there is provided a computer-implemented method of structuring content for training an artificial intelligence model, the method comprising: receiving (S11) input content associated with medical device documentation; converting (S12) the input content to a data interchange format; extracting (S13) a plurality of key terms from the converted input content; extracting (S14) a plurality of key phrases from the converted input content; receiving (S15) validation of the key terms and the key phrases from a supervisor; and building (S16) a dialogue, for training the artificial intelligence model, based on at least some of the validated key terms and the validated key phrases, wherein the dialogue comprises a series of statements.

According to an aspect, there is provided a computer-implemented method of structuring content for training an artificial intelligence model, the method comprising: receiving (S11) input content associated with medical device documentation; converting (S12) the input content to a data interchange format; extracting (S13) a plurality of key terms from the converted input content; extracting (S14) a plurality of key phrases from the converted input content; receiving (S15) validation of the key terms and the key phrases from a supervisor; and building (S16) a dialogue, for training the artificial intelligence model, based on at least some of the validated key terms and the validated key phrases, wherein the dialogue comprises a series of statements.