Abstract: A method and apparatus for training models in machine translation, an electronic device and a storage medium are disclosed, which relates to the field of natural language processing technologies and the field of deep learning technologies. An implementation includes mining similar target sentences of a group of samples based on a parallel corpus using a machine translation model and a semantic similarity model, and creating a first training sample set; training the machine translation model with the first training sample set; mining a negative sample of each sample in the group of samples based on the parallel corpus using the machine translation model and the semantic similarity model, and creating a second training sample set; and training the semantic similarity model with the second training sample set.

Abstract: Disclosed are a translation method, a classification model training method, a device and a storage medium, which relate to the field of computer technologies, particularly to the field of artificial intelligence such as natural language processing and deep learning. The translation method includes: obtaining a current processing unit of a source language text based on a segmented word in the source language text; determining a classification result of the current processing unit with a classification model; and in response to determining that the classification result is the current processing unit being translatable separately, translating the current processing unit to obtain translation result in a target language corresponding to the current processing unit.

Abstract: A display method, a method of training a semantic unit detection model, an electronic device, and a storage medium, which relate to a field of artificial intelligence technology, in particular to fields of natural language processing and machine translation technologies. The display method includes: acquiring a language sequence to be displayed; dividing the language sequence to be displayed into a plurality of semantic units with semantics; and converting the plurality of semantic units into subtitles for display one by one.

Abstract: A display method, an electronic device, and a storage medium, which relate to a field of natural language processing and a field of display. The display method includes: acquiring a content to be displayed; extracting a target term from the content using a term extraction rule; acquiring an annotation information for at least one target term, responsive to an extraction of the at least one target term; and displaying the annotation information for the at least one target term and the content.

Abstract: A method for text error correction includes: obtaining a text to be corrected; obtaining a pinyin sequence of the text to be corrected; and inputting the text to be corrected and the pinyin sequence to a text error correction model, to obtain a corrected text.

Abstract: Embodiments of the present disclosure provide a language conversion method and apparatus based on syntactic linearity and a non-transitory computer-readable storage medium. The method includes: encoding a source sentence to be converted by using a preset encoder to determine a first vector and a second vector corresponding to the source sentence; determining a current mask vector according to a preset rule, in which the mask vector is configured to modify vectors output by the preset encoder; determining a third vector according to target language characters corresponding to source characters located before a first source character; and decoding the first vector, the second vector, the mask vector, and the third vector by using a preset decoder to generate a target character corresponding to the first source character.

Abstract: The present disclosure provides a text error correction method, apparatus, electronic device and storage medium, and relates to the technical field of artificial intelligence such as natural language processing and deep learning. A specific implementation solution is: obtaining a current sentence and a historical sentence of the current sentence in an article to which the current sentence belongs; performing text error correction processing on the current sentence based on the current sentence and the historical sentence. According to the technical solutions of the present disclosure, text error correction can be performed on the current sentence based on the historical sentence, namely, the upper contextual information, of the current sentence in the article, so that the error correction information is richer and the error correction result is more accurate.

Abstract: Embodiments of the present disclosure provide a method and an apparatus for translating a polysemy, and a medium. The method includes: obtaining a source language text; identifying and obtaining the polysemy from the source language text; inquiring related words corresponding to each interpretation of the polysemy; determining a target interpretation corresponding to the related words contained in the source language text; and translating the polysemy into the target interpretation.

Abstract: A method and apparatus for training models in machine translation, an electronic device and a storage medium are disclosed, which relates to the field of natural language processing technologies and the field of deep learning technologies. An implementation includes mining similar target sentences of a group of samples based on a parallel corpus using a machine translation model and a semantic similarity model, and creating a first training sample set; training the machine translation model with the first training sample set; mining a negative sample of each sample in the group of samples based on the parallel corpus using the machine translation model and the semantic similarity model, and creating a second training sample set; and training the semantic similarity model with the second sample training set.

Abstract: A method for text translation includes obtaining a text to be translated; and inputting the text to be translated into a text translation model. The trained text translation model divides the text to be translated into a plurality of semantic units, determines N semantic units before a current semantic unit among the plurality of semantic units as local context semantic units, determines M semantic units before the local context semantic units as global context semantic units, and generates a translation result of the current semantic unit based on the local context semantic units and the global context semantic units. N is an integer, and M is an integer.

Abstract: A method and apparatus for translating speech are provided. The method may include: recognizing received to-be-recognized speech of a source language to obtain a recognized text; concatenating the obtained recognized text after a to-be-translated text, to form a concatenated to-be-translated text; inputting the concatenated to-be-translated text into a pre-trained discriminant model to obtain a discrimination result for characterizing whether the concatenated to-be-translated text is to be translated, where the discriminant model is used to characterize a corresponding relationship between a text and a discrimination result corresponding to the text; in response to the positive discrimination result being obtained, translating the concatenated to-be-translated text to obtain a translation result of a target language, and outputting the translation result.

Abstract: Presented herein are embodiments of a prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipates in a single translation. Within these frameworks are effective “wait-k” policy model embodiments that may be trained to generate a target sentence concurrently with a source sentence but lag behind by a predefined number of words. Embodiments of the prefix-to-prefix framework achieve low latency and better quality when compared to full-sentence translation in four directions: Chinese?English and German?English. Also presented herein is a novel latency metric that addresses deficiencies of previous latency metrics.

Abstract: A method for text error correction includes: obtaining a text to be corrected; obtaining a pinyin sequence of the text to be corrected; and inputting the text to be corrected and the pinyin sequence to a text error correction model, to obtain a corrected text.

Abstract: The present disclosure provides a machine translation model training method, apparatus, electronic device and storage medium, which relates to the technical field of natural language processing. A specific implementation solution is as follows: selecting, from parallel corpuses, a set of samples whose translation quality satisfies a preset requirement and which have universal-field features and/or target-field features, to constitute a first training sample set; selecting, from the parallel corpuses, a set of samples whose translation quality satisfies a preset requirement and which do not have universal-field features and target-field features, to constitute a second training sample set; training an encoder in the machine translation model in the target field, a discriminator configured in encoding layers of the encoder, and the encoder and a decoder in the machine translation model in the target field in turn with the first training sample set and second training sample set, respectively.

Abstract: Embodiments of the present disclosure provide a language conversion method and apparatus based on syntactic linearity and a non-transitory computer-readable storage medium. The method includes: encoding a source sentence to be converted by using a preset encoder to determine a first vector and a second vector corresponding to the source sentence; determining a current mask vector according to a preset rule, in which the mask vector is configured to modify vectors output by the preset encoder; determining a third vector according to target language characters corresponding to source characters located before a first source character; and decoding the first vector, the second vector, the mask vector, and the third vector by using a preset decoder to generate a target character corresponding to the first source character.

Abstract: Embodiments of the present disclosure provide a method and an apparatus for translating a polysemy, and a medium. The method includes: obtaining a source language text; identifying and obtaining the polysemy from the source language text; inquiring related words corresponding to each interpretation of the polysemy; determining a target interpretation corresponding to the related words contained in the source language text; and translating the polysemy into the target interpretation.

Abstract: A method and apparatus for translating speech are provided. The method may include: recognizing received to-be-recognized speech of a source language to obtain a recognized text; concatenating the obtained recognized text after a to-be-translated text, to form a concatenated to-be-translated text; inputting the concatenated to-be-translated text into a pre-trained discriminant model to obtain a discrimination result for characterizing whether the concatenated to-be-translated text is to be translated, where the discriminant model is used to characterize a corresponding relationship between a text and a discrimination result corresponding to the text; in response to the positive discrimination result being obtained, translating the concatenated to-be-translated text to obtain a translation result of a target language, and outputting the translation result.

Abstract: Presented herein are embodiments of a prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipates in a single translation. Within these frameworks are effective “wait-k” policy model embodiments that may be trained to generate a target sentence concurrently with a source sentence but lag behind by a predefined number of words. Embodiments of the prefix-to-prefix framework achieve low latency and better quality when compared to full-sentence translation in four directions: Chinese?English and German?English. Also presented herein is a novel latency metric that addresses deficiencies of previous latency metrics.