Abstract: The human-computer dialogue method includes: obtaining second historical dialogue data, current dialogue environment data, and second input dialogue data input by a user, determining a second semantic keyword based on the second historical dialogue data, the current dialogue environment data, and the second input dialogue data, and generating and outputting, based on the second semantic keyword and a preset-type knowledge base, second feedback dialogue data corresponding to the second input dialogue data, where the preset-type knowledge base includes: a knowledge graph, text knowledge, and external knowledge other than the knowledge graph and the text knowledge.

Abstract: A data processing method is provided, applied to the field of artificial intelligence. The method includes: determining, based on a target mapping relationship, one or more target network units corresponding to a target word vector and a storage address, where storage space corresponding to the storage address is located in storage space outside a computing unit; obtaining the one or more target network units from the storage space; and performing, through the computing unit based on the target word vector, a training process corresponding to a neural network constructed based on the one or more target network units. Because storage space of the storage location outside the computing unit may be set to be relatively large, through separation of storage and compute, a size of the large-scale model during training can be increased and scalability and flexibility of the large-scale model can be improved.

Abstract: The technology of this application relates to a response method in a human-computer dialogue, a dialogue system, and a storage medium, and belongs to the field of artificial intelligence. In a process of a dialogue between a user and a machine, a user intent of a current dialogue is determined based on an expected user intent associated with a sentence replied by the machine to the user in a previous dialogue, so that a response is made. Because processing logic for an expected user intent is introduced, accuracy of a generated response sentence is improved.

Abstract: A text processing method, a model training method, and an apparatus related to the field of artificial intelligence is provided. The method includes: obtaining target knowledge data; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.

Abstract: A data processing method includes processing target data through a target neural network to obtain a data processing result, where a target header of the target neural network is used to process, through a first transformation matrix, a first vector corresponding to first subdata, and process, through a second transformation matrix, a second vector corresponding to the first subdata, where the first vector corresponds to position information of the first subdata in the target data, and the second vector corresponds to semantic information of the first subdata.

Abstract: A missing semantics complementing method in the field of natural language processing in the artificial intelligence field is provided. The method includes: obtaining a question statement and a historical dialog statement; resolving a to-be-resolved item in the question statement based on the historical dialog statement and location information of the to-be-resolved item, to obtain a resolved question statement; determining whether a component in the question statement is ellipted, and if a component in the question statement is ellipted, complementing the ellipted component based on the historical dialog statement, to obtain a question statement after ellipsis resolution; merging the resolved question statement and the question statement after ellipsis resolution, to obtain a merged question statement; and determining a target complemented question statement from the resolved question statement, the question statement after ellipsis resolution, and the merged question statement.

Abstract: This application discloses a response determining method. The method includes: obtaining a to-be-responded first user statement; determining first state information of the first user statement based on the first user statement by using a state determining network, where the first state information includes a first dialog type of the first user statement; and inputting the first user statement and the first dialog type into a response generation network, to obtain a response corresponding to the first user statement.

Abstract: A text data processing method, a neural-network training method, and related devices are provided. The methods may be applied to the text data processing field in the artificial intelligence field. The method includes: obtaining a to-be-processed text, where the to-be-processed text includes a plurality of characters; and processing the to-be-processed text by using a target model to obtain a prediction result, where the prediction result indicates to split the to-be-processed text into a plurality of target character sets, the prediction result further includes a plurality of first labels, one first label indicates semantics of one target character set, and the plurality of first labels are used to determine an intention of the to-be-processed text.

Abstract: A natural language processing method includes obtaining a to-be-processed phrase, where the to-be-processed phrase includes M words, determining polarity characteristic information of m to-be-processed words in the M words, where polarity characteristic information of an ith word in the m to-be-processed words includes n polarity characteristic values, and each polarity characteristic value corresponds to one sentiment polarity, determining a polarity characteristic vector of the to-be-processed phrase based on the polarity characteristic information of the m to-be-processed words, where the polarity characteristic vector includes n groups of components in a one-to-one correspondence with n sentiment polarities, and determining a sentiment polarity of the to-be-processed phrase based on the polarity characteristic vector of the to-be-processed phrase using a preset classifier, and outputting the sentiment polarity.

Abstract: The technology of this application relates to a response method in a human-computer dialogue, a dialogue system, and a storage medium, and belongs to the field of artificial intelligence. In a process of a dialogue between a user and a machine, a user intent of a current dialogue is determined based on an expected user intent associated with a sentence replied by the machine to the user in a previous dialogue, so that a response is made. Because processing logic for an expected user intent is introduced, accuracy of a generated response sentence is improved.

Abstract: This application relates to the field of artificial intelligence, and provides a text processing method, a model training method, and an apparatus. The method includes: obtaining target knowledge data; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.

Abstract: The present invention discloses a missing semantics complementing method in the field of natural language processing in the artificial intelligence field, including: obtaining a question statement and a historical dialog statement; resolving a to-be-resolved item in the question statement based on the historical dialog statement and location information of the to-be-resolved item, to obtain a resolved question statement; determining whether a component in the question statement is ellipted, and if a component in the question statement is ellipted, complementing the ellipted component based on the historical dialog statement, to obtain a question statement after ellipsis resolution; merging the resolved question statement and the question statement after ellipsis resolution, to obtain a merged question statement; and determining a target complemented question statement from the resolved question statement, the question statement after ellipsis resolution, and the merged question statement.

Abstract: Embodiments of the present invention relate to the field of computer technologies, and provide a search method and apparatus to resolve a problem that a reference text, of a text in a professional field, that is determined by using the prior art has relatively low accuracy. The method includes: obtaining n named entities in a current to-be-analyzed target case (S300); determining a first characteristic and a second characteristic (S301); generating, based on the first characteristic and the second characteristic and according to a preset vector generation rule, a target characteristic vector corresponding to the target case (S302); obtaining each historical case in a database and a characteristic vector corresponding to each historical case (S303); and separately calculating a similarity between the target characteristic vector and the characteristic vector corresponding to each historical case, and selecting a historical case whose similarity result meets a preset condition as a reference case (S304).

Abstract: A classification model training method includes obtaining a positive training set and a first negative training set, where the positive training set includes samples of a positive sample set in a corpus, where the first negative training set includes samples of an unlabeled sample set in the corpus, training, using the positive training set and the first negative training set, to obtain a first classification model, determining, using the first classification model, a pseudo negative sample in the first negative training set, removing the pseudo negative sample from the first negative training set, updating the first negative training set to a second negative training set, and training, using the positive training set and the second negative training set, to obtain a target classification model.

Abstract: This application provides a natural language processing method and apparatus, to accurately determine a sentiment polarity of a word.

Abstract: A classification model training method includes obtaining a positive training set and a first negative training set, where the positive training set includes samples of a positive sample set in a corpus, where the first negative training set includes samples of an unlabeled sample set in the corpus, training, using the positive training set and the first negative training set, to obtain a first classification model, determining, using the first classification model, a pseudo negative sample in the first negative training set, removing the pseudo negative sample from the first negative training set, updating the first negative training set to a second negative training set, and training, using the positive training set and the second negative training set, to obtain a target classification model.

Abstract: Embodiments of the present invention relate to the field of computer technologies, and provide a search method and apparatus to resolve a problem that a reference text, of a text in a professional field, that is determined by using the prior art has relatively low accuracy. The method includes: obtaining n named entities in a current to-be-analyzed target case (S300); determining a first characteristic and a second characteristic (S301); generating, based on the first characteristic and the second characteristic and according to a preset vector generation rule, a target characteristic vector corresponding to the target case (S302); obtaining each historical case in a database and a characteristic vector corresponding to each historical case (S303); and separately calculating a similarity between the target characteristic vector and the characteristic vector corresponding to each historical case, and selecting a historical case whose similarity result meets a preset condition as a reference case (S304).