Abstract: An electronic device is provided. The electronic device includes a memory and a processor. The processor is configured to, based on acquiring a first sentence in a first language, determine whether to correct the first sentence to another sentence in the first language by using a second language model trained based on a learning corpus, and based on determining to correct the first sentence to another sentence in the first language, input the first sentence into a conversion model trained to acquire another sentence having a similarity greater than or equal to a threshold value to an input sentence and acquire a second sentence in the first language which is a corrected form of the first sentence, and based on acquiring the second sentence, input the second sentence into a translation model trained based on the learning corpus and acquire a third sentence in a second language.

Abstract: A system and method incorporate prior knowledge into the optimization and regularization of a classification and regression model. The optimization may be a regularization process and the prior knowledge may be incorporated through adjustment of a cost function. A method of at least one processor developing a classification and regression model may be provided. The method may be implemented by at least one processor that implements classification and regression model functionality, including receiving training data and adjusting the model according to the training data; testing the classification and regression model; and employing prior knowledge during an optimization of the classification and regression model. The regularizing can include adjusting feature weights according to prior knowledge. In various embodiments, such systems and methods can be used in the processing of language inputs, e.g., speech and/or text inputs, to achieve greater interpretation accuracy.

Abstract: Provided is technology for assessing whether uttered speech detected from input speech is speech suited to a prescribed purpose. A method comprises detecting, from input speech including speech uttered by a speaker and noise, the uttered speech corresponding to the speech uttered by the speaker, extracting an acoustic feature of the uttered speech, generating, from the uttered speech, a speech recognition result set with a recognition score, generating, from the speech recognition result set with the recognition score, a speech recognition result word vector expression set and a speech recognition result part-of-speech vector expression set, generating a target utterance estimation model, providing, using the target utterance estimation model, a probability of the uttered speech being suited to the prescribed purpose, and outputting the uttered speech and the speech recognition result set with the recognition score, the the uttered speech suitable to the prescribed purpose.

Abstract: The disclosure may provide a method for obtaining a document layout, an electronic device, and a storage medium. The method may include: obtaining a plurality of pieces of first sample data; extracting structured information from each of the plurality of pieces of first sample data as target structured information corresponding to each of the plurality of pieces of first sample data; inputting the plurality of pieces of first sample data into an initial text generation model to generate predicted structured information corresponding to each of the plurality of pieces of first sample data; generating a first loss value based on a difference between the predicted structured information corresponding to each of the plurality of pieces of first sample data and the corresponding target structured information; and training a phrase generation ability of the initial text generation model based on the first loss value to generate the text generation model.

Abstract: Dynamic interfacing with applications is provided. For example, a system receives a first input audio signal. The system processes, via a natural language processing technique, the first input audio signal to identify an application. The system activates the application for execution on the client computing device. The application declares a function the application is configured to perform. The system modifies the natural language processing technique responsive to the function declared by the application. The system receives a second input audio signal. The system processes, via the modified natural language processing technique, the second input audio signal to detect one or more parameters. The system determines that the one or more parameters are compatible for input into an input field of the application. The system generates an action data structure for the application. The system inputs the action data structure into the application, which executes the action data structure.

Abstract: The present disclosure relates to concurrent learning of a relationship estimation model and a phrase generation model. The relationship estimation model estimates a relationship between phrases. The phrase generation model generates a phrase that relates to an input phrase. The phrase generation model includes an encoder and a decoder. The encoder converts a phrase into a vector using a three-piece set as learning data. The decoder generates, based on the converted vector and a connection expression or a relationship label, a phrase having a relationship expressed by the connection expression or the relationship label for the phrase. The relationship estimation model generates a relationship score from the converted vector, which indicates each phrase included in a combination of the phrases, and a vector indicating the connection expression and the relationship label.

Abstract: A method and an electronic device for detecting crosstalk data are provided. The method for detecting crosstalk data can detect whether an audio data stream includes crosstalk data. The method includes: receiving a first audio data block, a second audio data block, and a reference time difference, wherein the first audio data block and the second audio data block separately include a plurality of audio data segments; using a time difference between an acquisition time of an audio data segment in the first audio data block and a corresponding audio data segment in the second audio data block as an audio segment time difference; and determining that the audio data segment of the first audio data block includes crosstalk data when the audio segment time difference does not match the reference time difference.

Abstract: The present disclosure provides a method, apparatus, electronic device and storage medium for processing a semantic representation model, and relates to the field of artificial intelligence technologies. A specific implementation solution is: collecting a training corpus set including a plurality of training corpuses; training the semantic representation model using the training corpus set based on at least one of lexicon, grammar and semantics. In the present disclosure, by building the unsupervised or weakly-supervised training task at three different levels, namely, lexicon, grammar and semantics, the semantic representation model is enabled to learn knowledge at levels of lexicon, grammar and semantics from massive data, enhance the capability of universal semantic representation and improve the processing effect of the NLP task.

Abstract: Dynamic interfacing with applications is provided. For example, a system receives a first input audio signal. The system processes, via a natural language processing technique, the first input audio signal to identify an application. The system activates the application for execution on the client computing device. The application declares a function the application is configured to perform. The system modifies the natural language processing technique responsive to the function declared by the application. The system receives a second input audio signal. The system processes, via the modified natural language processing technique, the second input audio signal to detect one or more parameters. The system determines that the one or more parameters are compatible for input into an input field of the application. The system generates an action data structure for the application. The system inputs the action data structure into the application, which executes the action data structure.

Abstract: An intention identification method includes generating a heterogeneous text network based on a language material sample; using a graph embedding algorithm to perform learning with respect to the heterogeneous text network and obtain a vector representation of the language material sample and a word, and determining keywords of the language material sample based on a similarity in terms of a vector between the language material sample and the word in the language material sample; training an intention identification model until a predetermined training termination condition is satisfied, by using the keywords of the language material samples, and obtaining the trained intention identification model; and receiving a language material query, and using the trained intention identification model to identify an intention of the language material query.

Abstract: A machine-learning method for training a decision-making model includes: obtaining a rationale vector group for a rationale included in a labeled natural language text file; assembling an effective vector group for the labeled natural language text file by connecting the rationale vector groups for the rationales using a specific order; and executing a supervised classification algorithm to train the decision-making model using the effective vector group and a target decision for the natural language text file. The decision-making model is trained to be configured to label an unlabeled natural language text file using one of a plurality of potential decisions that serves as a target decision.

Abstract: Training and/or using a multilingual classification neural network model to perform a natural language processing classification task, where the model reuses an encoder portion of a multilingual neural machine translation model. In a variety of implementations, a client device can generate a natural language data stream from a spoken input from a user. The natural language data stream can be applied as input to an encoder portion of the multilingual classification model. The output generated by the encoder portion can be applied as input to a classifier portion of the multilingual classification model. The classifier portion can generate a predicted classification label of the natural language data stream. In many implementations, an output can be generated based on the predicted classification label, and a client device can present the output.