Tencent Technology (Shenzhen) Company Limited

Alibaba Group Holding Limited

Huawei Technologies Co., Limited

Zhejiang University

Shenzhen Intellirocks Tech. Co., Ltd.

Shenzhen Xinghe Pixel Electronics Co., Ltd

Jie Zhou

Fandong Meng

Cheng Niu

Peng Li

Jinchao Zhang

Wen He

ShuShi Jia

Yan Zhang

Jin Zhang

Jian Hua Liu

Yan Wei Zhang

Xiaozhen Fu

Jie Cao

Qiuge Liu

Yizhang Tan

Shuo Sun

Le Tian

Mei He

Xufei Zhang

Randy Zhong

Wenlong Wu

Jian Xu

Zheng Wang

Tianyu Gao

Xun Luo

Sheng Li

Huizhen Qian

Hao Peng

Yijin Liu

Xiao Zhou

Shushi Jia

Qiu Ran

Fan Dong Meng

Baihan Kong

Yankai Lin

Zhiyuan Liu

Dengcheng He

Guanghui Liu

Xu Han

Huiqin Yuan

Xiao Feng

Jinan Xu

Xiaobin Cao

Xiaosheng Liu

Guangming Song

Weiye Zhang

Huichao Hu

Daoxin Wang

Zhi Yin

Youhe Zhang

Zhongjian He

Yibo Jin

Bo Tang

JinLin Li

Zeyang Lei

Zekang Li

Maosong Sun

Feilong Chen

Xiuyi Chen

Yongjing Yin

Jinsong Su

Guangmin Zhou

Yun Long Liang

Jin An Xu

Wei Hu

Jinlin Li

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

Disclosed is a text sentence processing method performed by a computer device, including: acquiring sample text sentences including entity pairs and relationship labels of the entity pairs; extracting positive and negative example sentence pairs from the sample text sentences according to the relationship labels, and performing positive-negative example sampling, to obtain a training set; inputting the training set into a relationship extraction model to generate loss values; and adjusting parameters of the relationship extraction model according to the loss values, and repeating the step of extracting positive and negative example sentence pairs from the sample text sentences according to the relationship labels to perform iterative training of the relationship extraction model until a training end condition is met, to obtain an updated relationship extraction model, the relationship extraction model being configured to identify an entity relationship of an entity pair in an input text sentence.

Text sentence processing method and apparatus, computer device, and storage medium

An instruction transmission method is provided for an ambient lamp. The method includes: sequentially obtaining a playback frame from a playback frame sequence as a current playback frame; determining a target encoding scheme of the current playback frame based on a frame type of the current playback frame; determining effective data and a data type of the effective data of the current playback frame according to the target encoding scheme, and encoding the effective data into playback encoded data; and encapsulating the playback encoded data of the current playback frame and the data type of the effective data into a lighting-effect playback instruction, and transmitting the lighting-effect playback instruction to a control chip of a lighting component of the ambient lamp for execution.

Ambient lamp and instruction transmission/application method thereof, and 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

An electronic device obtains a to-be-translated sentence. The electronic device divides the to-be-translated sentence into a preset quantity of clauses. The electronic device separately translates each of the clauses to obtain a respective translation result corresponding to each of the clauses. The electronic device combines the respective translation results corresponding to each of the clauses according to semantics to obtain a target translation sentence corresponding to the to-be-translated sentence.

Translation method and apparatus, electronic device, and computer-readable 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

Spider web light

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 method including determining a database table for which a database index is to be created, wherein the database table comprises a spatial field for storing spatial data; acquiring, for the database table, a spatial filter condition comprising a spatial field ID; and generating, according to the spatial filter condition, a tree-structured spatial index for the database table, wherein a leaf node of the tree-structured spatial index stores therein spatial data meeting the spatial filter condition and its primary key ID. The efficiency of queries related to spatial data is thus enhanced.

Database index and database query processing method, apparatus, and device

An encoding method is provided for an encoding apparatus. The method includes obtaining a target paragraph and a preset database, and inputting the target paragraph and preset database into a memory encoding model, obtaining, in an input layer, an original vector set of the target paragraph and a knowledge vector set of the preset database, obtaining, in a first memory layer, a first target sentence matrix according to the original vector set and the knowledge vector set, and obtaining, in an output layer, a paragraph vector of the target paragraph according to the first target sentence matrix, and performing processing based on the paragraph vector.

Encoding method, apparatus, and 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

Embodiments of the disclosure provide an information processing method, an information processing apparatus, and a storage medium. The method includes: obtaining source data; encoding sub-data in the source data based on a target word feature vector to obtain hidden feature vectors corresponding to the sub-data, the target word feature vector representing a sentiment feature standard; obtaining a word feature vector corresponding to the source data based on the hidden feature vectors corresponding to the sub-data; and inputting the word feature vector into a preset sentiment classification network to obtain a result of sentiment polarity prediction of the source data. According to the embodiments of the disclosure, the accuracy of sentiment polarity prediction may be improved.

Information processing method and apparatus, and storage medium

Embodiments of this disclosure include an encoding method and apparatus. The encoding may include obtaining a target paragraph and a context sentence of the target paragraph, and inputting the target paragraph and the context sentence into a memory encoding model. The encoding may further include obtaining an original vector set and a memory vector set in the input layer and obtaining a first target sentence matrix of the original vector set in the memory layer according to the original vector set and the memory vector set. The encoding may further include obtaining a paragraph vector of the target paragraph in the output layer according to the first target sentence matrix and performing processing based on the paragraph vector.

Encoding method, apparatus, and storage medium

The disclosure discloses a method and an apparatus for training a dialog generation model, and a dialog generation method and apparatus, and relates to the field of artificial intelligence. The method includes: encoding a context sample to obtain a first latent variable, and recognizing the first latent variable to obtain a prior latent variable; encoding a response sample to obtain a second latent variable; encoding a response similar sample to obtain a third latent variable; performing recognition according to a Gaussian mixture distribution of the first latent variable, the second latent variable, and the third latent variable to obtain a posterior latent variable; and matching the prior latent variable with the posterior latent variable, and performing adversarial training on a dialog generation model.

Method and apparatus for training dialog generation model, dialog generation method and apparatus, and medium

Growing community of inventors

Hangzhou, China

Jie Zhou