Tencent Technology (shenzhen) Company Limited

Fandong Meng

Jie Zhou

Jinchao Zhang

Peng Li

Yang Liu

Yong Cheng

Zhaopeng Tu

Yang Feng

Junjie Zhai

Jinan Xu

Feilong Chen

Xiuyi Chen

Jiao Ou

Yongjing Yin

Jinsong Su

Disclosed in this application are a visual content dialog method performed by an electronic device. The method includes: acquiring an image feature of an input image and state vectors corresponding to first n rounds of historical question answering dialog, n being a positive integer; acquiring a question feature of a current round of questioning related to the input image; performing multimodal encoding on the image feature of the input image, the state vectors corresponding to the first n rounds of historical question answering dialog, and the question feature of the current round of questioning, to obtain a state vector corresponding to the current round of questioning; and performing multimodal decoding on the state vector corresponding to the current round of questioning and the image feature of the input image, to obtain an actual output answer corresponding to the current round of questioning.

Visual dialog method and apparatus, method and apparatus for training visual dialog model, electronic device, and computer-readable storage medium

A dialogue generation method, a network training method and apparatus, a storage medium, and a device are provided. The method includes: predicting, based on a plurality of a plurality of pieces of candidate knowledge text in a first candidate knowledge set, a preliminary dialogue response of a first dialogue preceding text; processing the first dialogue preceding text based on the preliminary dialogue response to obtain a first dialogue preceding text vector; obtaining a piece of target knowledge text based on a probability value of the piece of target knowledge text of being selected to be used in generating a final dialogue response, the probability value being obtained based on the first dialogue preceding text vector; and generating the final dialogue response based on the first dialogue preceding text and the piece of target knowledge text.

Dialogue generation method and network training method and apparatus, storage medium, and device

A computer device acquires, based on a prior network and a posterior network of a dialogue model, at least two first dialogue features and at least two second dialogue features of a first dialogue. The computer device outputs, using the prior network, a probability distribution of dialogue features in accordance with the acquired dialogue features and estimates, using the posterior network, the probability distribution of the dialogue features output by the prior network. The computer device updates the dialogue model and updates the posterior network based on dialogue features of the first dialogue. The computer device also updates a discriminator in the dialogue model based on at least two first dialogue features and at least two second dialogue features of a second dialogue. In accordance with a determination that the dialogue model has satisfied a training end condition, the computer device determines that the dialogue model is a trained model.

Method and apparatus for training dialog model, computer device, and storage medium

A method and apparatus for generating a hidden state in a recurrent neural network for language processing are provided. The method includes: generating regional word vectors of at least two dimensions of a target word vector inputted at a first moment; combining the regional word vectors to obtain combined regional word vectors of at least two dimensions; performing aggregation transformation processing on the combined regional word vectors based on a feedforward neural network, to obtain an aggregated word vector corresponding to the target word vector; and generating a target hidden state corresponding to the target word vector based on the aggregated word vector.

Method and apparatus for generating hidden state in recurrent neural network for language processing

Embodiments of this disclosure disclose a sentence processing method and device. The method may include performing word segmentation operation on a source sentence to be encoded to obtain m words. The method may further include obtaining an iword in the m words using an iencoding processing node in the n encoding processing nodes, and obtaining an (i−1)word vector from an (i−1)encoding processing node. The method may further include performing linear operation and non-linear operation on the iword and the (i−1)word vector using the first unit of the iencoding processing node to obtain an ioperation result, and outputting the ioperation result to the at least one second unit for processing to obtain an iword vector. The method may further include generating, in response to obtaining m word vectors, a sentence vector according to the m word vectors.

Sentence encoding and decoding method, storage medium, and device

A computer device acquires a semantic association graph associated with n source statements belonging to different modals. The semantic association graph includes n semantic nodes of the different modals, a first connecting edge used for connecting the semantic nodes of a same modal and a second connecting edge used for connecting the semantic nodes of different modals. The computer device extracts a plurality of first word vectors from the semantic association graph. The device encodes the plurality of first word vectors to obtain n encoded feature vectors. The device also decodes the n encoded feature vectors to obtain a translated target statement.

Translation method and apparatus based on multimodal machine learning, device, and storage medium

A data processing method includes: obtaining a to-be-detected text, and determining a context word set and a candidate substitute word set corresponding to a to-be-detected word in the to-be-detected text to be inputted into a pronoun resolution neural network for feature extraction; performing positive-example iteration processing and negative-example iteration processing on the features corresponding to the context word set and the candidate substitute word set, to obtain a positive-example feature vector length and a negative-example feature vector length, and calculating a substitute probability corresponding to each candidate substitute word in the candidate substitute word set according to the positive-example feature vector length and the negative-example feature vector length; determining a target substitute word according to the substitute probability corresponding to the each candidate substitute word; and inserting the target substitute word into the to-be-detected text according to a position corresponding to the to-be-detected word, to obtain a target text.

Data processing method and pronoun resolution neural network training method

A translation model training method for a computer device includes obtaining a training sample set, the training sample set including a plurality of training samples. Each training sample is a training sample pair having a training input sample in a first language and a training output sample in a second language. The method also includes determining a disturbance sample set corresponding to each training sample in the training sample set, the disturbance sample set comprising at least one disturbance sample, and a semantic similarity between the disturbance sample and the corresponding training sample being greater than a first preset value; and training an initial translation model by using the plurality of training samples and the disturbance sample set corresponding to each training sample to obtain a target translation model, such that the training output sample remains same for the disturbance sample and the corresponding training sample.

Translation model training method, sentence translation method, device, and storage medium

A language sequence labeling method and includes: reading a first embedding representation of a language sequence, the first embedding representation including a character-level word embedding representation, a pre-trained word embedding representation, and a global word embedding representation of the language sequence, the global word embedding representation referring to a global context representation of the language sequence; performing first depth transformation (DT) encoding on the first embedding representation based on a first DT recurrent neural network (RNN), to output a first hidden-layer state representation corresponding to each word in the language sequence; and decoding the first hidden-layer state representations of the language sequence, to obtain a labeling result of one or more elements in the language sequence.

Growing community of inventors

Shenzhen, China

Fandong Meng