Abstract: A translation method includes: selecting a source word from a source sentence; generating mapping information including location information of the selected source word mapped to the selected source word in the source sentence; and correcting a target word, which is generated by translating the source sentence, based on location information of a feature value of the target word and the mapping information.

Abstract: An electronic device includes one or more processors and a memory storing instructions configured to, when executed by the one or more processors, cause the one or more processors to: implement a machine learning-based conditional generative model configured to reconstruct target data from latent vectors, the conditional generative model trained based on an existing data set for a target task; determine an extrapolation weight; generate an augmented latent vector and augmented condition data by extrapolating, based on the extrapolation weight, from a latent vector corresponding to the existing dataset and from existing condition data corresponding to the existing dataset; and generate a new dataset comprising augmented target data generated by the conditional generative model based on the augmented condition data and based on the augmented latent vector.

Abstract: A processor-implemented method includes performing speech recognition of a speech signal, generating a plurality of first candidate sentences as a result of the performing of the speech recognition, identifying a respective named entity in each of the plurality of first candidate sentences, determining a standard expression corresponding to the identified respective named entity using phonemes of the corresponding named entity, determining whether to replace the identified named entity in each of the plurality of first candidate sentences with the determined standard expression based on a similarity between the named entity and the standard expression corresponding to the named entity and determining a plurality of second candidate sentences based on the determination result; and outputting a final sentence selected from the plurality of second candidate sentences.

Abstract: A model training method and apparatus is disclosed, where the model training method acquires a recognition result of a teacher model and a recognition result of a student model for an input sequence and trains the student model such that the recognition result of the teacher model and the recognition result of the student model are not distinguished from each other.

Abstract: A processor implemented method to update a sentence generation model includes: generating a target sentence corresponding to a source sentence using a first decoding model; calculating reward information associated with the target sentence using a second decoding model configured to generate a sentence in an order different from an order of the sentence generated by the first decoding model; and generating an updated sentence generation model by resetting a weight of respective nodes in the first decoding model based on the calculated reward information.

Abstract: Provided is a method and apparatus for determining a molecular conformation. The method of determining a molecular conformation includes generating candidate conformations based on one or more artificial neural network (ANN)-based conformation generative model that is based on an artificial neural network (ANN), comparing energy values between the candidate conformations by inputting the candidate conformations to an ANN-based conformation selecting model, and determining a final conformation based on a result of the comparing.

Abstract: A speech generation method and apparatus are disclosed. The speech generation method includes obtaining, by a processor, a linguistic feature and a prosodic feature from an input text, determining, by the processor, a first candidate speech element through a cost calculation and a Viterbi search based on the linguistic feature and the prosodic feature, generating, at a speech element generator implemented at the processor, a second candidate speech element based on the linguistic feature or the prosodic feature and the first candidate speech element, and outputting, by the processor, an output speech by concatenating the second candidate speech element and a speech sequence determined through the Viterbi search.

Abstract: A model training method and apparatus is disclosed, where the model training method acquires a recognition result of a teacher model and a recognition result of a student model for an input sequence and trains the student model such that the recognition result of the teacher model and the recognition result of the student model are not distinguished from each other.

Abstract: A translation method includes: selecting a source word from a source sentence; generating mapping information including location information of the selected source word mapped to the selected source word in the source sentence; and correcting a target word, which is generated by translating the source sentence, based on location information of a feature value of the target word and the mapping information.

Abstract: A model training method and apparatus is disclosed, where the model training method acquires a recognition result of a teacher model and a recognition result of a student model for an input sequence and trains the student model such that the recognition result of the teacher model and the recognition result of the student model are not distinguished from each other.

Abstract: A decoding method, the method including: receiving an input sequence corresponding to an input speech at a current time; and in a neural network (NN) for speech recognition, generating an encoded vector sequence by encoding the input sequence, determining reuse tokens from candidate beams of two or more previous times by comparing the candidate beams of the previous times, and decoding one or more tokens subsequent to the reuse tokens based on the reuse tokens and the encoded vector sequence.

Abstract: A translation method includes: selecting a source word from a source sentence; generating mapping information including location information of the selected source word mapped to the selected source word in the source sentence; and correcting a target word, which is generated by translating the source sentence, based on location information of a feature value of the target word and the mapping information.

Abstract: A processor-implemented electronic device input method includes: identifying input items configured to receive information on a displayed screen, by performing either one or both of a layout analysis and an image analysis with respect to the screen; tagging one of the input items with a text token extracted from a speech recognition result of a speech signal; and inputting the tagged text token into the one of the input items.

Abstract: A model training method and apparatus is disclosed, where the model training method acquires first output data of a student model for first input data and second output data of a teacher model for second input data and trains the student model such that the first output data and the second output data are not distinguished from each other. The student model and the teacher model have different structures.

Abstract: Disclosed is a dialogue management method and apparatus. The dialogue management method includes sequentially resolving an application domain to provide a service to a user, a function appropriate for an intent of a user from among functions of the application domain, and at least one slot to perform the function, adaptively determining an expression scheme of a dialogue management interface depending on a progress of the sequentially resolving, and displaying the dialogue management interface.

Abstract: A method and computing device with classification verification is provided. A processor-implemented method includes implementing a classification neural network to generate a classification result of data input to the classification neural network by generating, with respect to the input data, intermediate hidden values of one or more hidden layers of the classification neural network, generating the classification result of the input data based on the generated intermediate hidden values, and generating a determination of a reliability of the classification result by implementing a verification neural network, input the intermediate hidden values, to generate the determination of the reliability.

Abstract: A speech recognition method includes receiving a sentence generated through speech recognition, calculating a degree of suitability for each word in the sentence based on a relationship of each word with other words in the sentence, detecting a target word to be corrected among the words in the sentence based on the degree of suitability for each word, and replacing the target word with any one of candidate words corresponding to the target word.

Abstract: A processor-implemented text-to-speech method includes determining, using a sub-encoder, a first feature vector indicating an utterance characteristic of a speaker from feature vectors of a plurality of frames extracted from a partial section of a first speech signal of the speaker, and determining, using an autoregressive decoder, into which the first feature vector is input as an initial value, from context information of the text, a second feature vector of a second speech signal in which a text is uttered according to the utterance characteristic.

Abstract: A processor-implemented machine translation method includes translating a source sentence expressed in a source language into a target language to determine a target sentence, determining, based on a reliability of the target sentence, whether the target sentence is appropriate as a translation result of the source sentence, and re-determining a target sentence corresponding to the source sentence in response to a result of the determining being that the target sentence is inappropriate as the translation result.

Abstract: A processor-implemented method includes performing speech recognition of a speech signal, generating a plurality of first candidate sentences as a result of the performing of the speech recognition, identifying a respective named entity in each of the plurality of first candidate sentences, determining a standard expression corresponding to the identified respective named entity using phonemes of the corresponding named entity, determining whether to replace the identified named entity in each of the plurality of first candidate sentences with the determined standard expression based on a similarity between the named entity and the standard expression corresponding to the named entity and determining a plurality of second candidate sentences based on the determination result; and outputting a final sentence selected from the plurality of second candidate sentences.