Beijing Baidu Netcom Science Technology Co., Ltd

Chongqing Boe Optoelectronics Technology Co., Ltd.

Boe Technology Group Co., Ltd.

Chinese Academy of Sciences

Beijing Baidu Netcom Science and Technology Co., Ltd.

International Business Machines Corporation

Beijing Boe Technology Development Co., Ltd.

Beijing University of Technology

Chinese Academy of Geological Sciences

Beijing Boe Display Technology Co., Ltd.

Gccalliance Inc.

Zhi Li

Wei Li

Hua Wu

Zhongjun He

Ruiqing Zhang

Hui Liu

Yu Wang

Ke Liao

Wencheng Luo

Chuanqiang Zhang

Hening Zhang

Jinhong Zhang

Haifeng Wang

Yansheng Sun

Zhanyi Liu

Meilong Hu

Peng Hui Jiang

Hao Chen

Bin Zhang

Jing Liu

Jing Wang

Ning Li

Zhiqiang Wang

Zhanchang Bu

Yao Liang Chen

Bo Tong Liu

Xiao Dong Li

Xing Xing Shen

Sijun Lei

Jing Yu

Hetao Wang

Yuqing Li

Kun Lu

Xiao Feng

Ming Yue

Bin Cao

Chaojie Zhang

Namin Kwon

Lin Zhao

He Jiang Jia

Minghui Ma

Jinhu Cao

Xiyang Wang

Qiong Yuan

Bowen Xiong

Wei Ran

Weiqiang Liu

Kai Yan

Wenqi Quan

Xin Cen

Shuquan Sun

Fengwu Yu

Shuangshuang Cui

Yongzheng Xin

Fengtao Huang

Wen Chen

Aimin Du

Jiaxin Yu

Xing Wan

Jingxuan Zhao

Sheng Jie Bj Han

Yiming Cheng

Jianzhong Zhao

Shengjie Yin

Yumei Zhou

Wen Zhang

Xinlei Cao

Enke Guo

Stone Tseng

Hanbing Song

Wei Di

Pengfei Tian

Jingbo Sun

Ruxin Ding

Qiuyi Du

Ze Shen

Shuangfeng Zhao

Hongguo Zhang

Yantao Yin

Ye Tian

A method for training a non-autoregressive translation (NAT) model includes: acquiring a source language text, a target language text corresponding to the source language text and a target length of the target language text; generating a target language prediction text and a prediction length by inputting the source language text into the NAT model, in which initialization parameters of the NAT model are determined based on parameters of a pre-trained translation model; and obtaining a target NAT model by training the NAT model based on the target language text, the target language prediction text, the target length and the prediction length.

Method for training non-autoregressive translation model

A backlight module includes a light-emitting substrate, at least one chip-on-film and a backplane. The light-emitting substrate includes a signal line group and a plurality of light-emitting units, and the plurality of light-emitting units are electrically connected to the signal line group. The at least one chip-on-film is arranged on a non-light exit side of the light-emitting substrate, and electrically connected to the signal line group. The backplane is disposed on the non-light exit side of the light-emitting substrate, and the at least one chip-on-film is located between the backplane and the light-emitting substrate. The backplane is provided with a groove therein, a notch of the groove faces the light-emitting substrate, and at least portion of a chip-on-film film of the at least one chip-on-film is disposed in the groove.

Backlight module, display module and display apparatus

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.

Display method, method of training semantic unit detection model, electronic device, and storage medium

A light-emitting module, a light-emitting substrate, and a display device are provided. The light-emitting module includes a plurality of light-emitting elements, the plurality of light-emitting elements are arranged in a row direction and a column direction, the plurality of light-emitting elements are formed into a plurality of columns of light-emitting elements, at least one column of light-emitting elements among the plurality of columns of light-emitting elements include a first light-emitting element, a second light-emitting element, a third light-emitting element, and a fourth light-emitting element that are arranged sequentially, and the second light-emitting element and the fourth light-emitting element are arranged on both sides of a center connection line of the first light-emitting element and the third light-emitting element, respectively.

Light-emitting module, light-emitting substrate, and display device

Provided is a signal driving system with a constant slew. The signal driving system with the constant slew includes: a step voltage generation unit configured to provide multiplex arithmetic gradient voltage signals; a multiplexer, wherein an input end of the multiplexer is connected to the step voltage generation unit to receive the multiplex arithmetic gradient voltage signals, and another input end of the multiplexer is connected to a control signal generation unit, and the multiplexer is configured to selectively output the multiplex arithmetic gradient voltage signals under a control of a control signal generated by the control signal generation unit; a voltage following unit connected to the multiplexer, wherein the voltage following unit is configured to serve as an isolation and improve a driving ability; and an output following unit connected to the voltage following unit, wherein the output following unit is configured to drive a subsequently-connected load unit.

Signal driving system with constant slew rate

A large-scale denudation depth thematic mapping method, which includes: creating a rule for arranging field work point and field work route, a sampling rule, a field observation and recording rule and a mineral processing rule of a research area. Analyzing a target mineral selected at each field work point by using a thermochronology research method and inputting analysis data into a Low-T Thermo software to perform thermal evolution history modeling and denudation depth calculation, so as to obtain a denudation depth at each of the field work points. Drawing a denudation depth isopleth map of the research area according to the denudation depth at each of the field work points; and setting a large-scale standard regional geological map of the research area as a base map. Superimposing the base map and the denudation depth isopleth map to obtain a denudation depth map of the research area.

Large-scale denudation depth thematic mapping method

A text translation method is described that includes initially acquiring text. Thereafter, first text is determined in the initial text; and second text is determined according to the first text, where the second text is used for describing the first text. Additionally, initial text is translated to obtain initial translation text, and the second text is translated to obtain description translation text. Thereafter, the initial translation text is updated according to the description translation text to obtain target translation text of the initial text.

Text translation method and apparatus, electronic device, and storage medium

A machine translation method includes: obtaining first target language text by performing first translation on source language text using an initial NMT model; identifying an untranslated part in the source language text based on the source language text and the first target language text; obtaining an adjusted NMT model by increasing an attention weight corresponding to the untranslated part in the initial NMT mode; and obtaining second target language text by performing second translation on the source language text using the adjusted NMT model.

Machine translation method and apparatus, device and storage medium

A training method, a text translation method, an electronic device, and a storage medium, which relate to a field of artificial intelligence, in particular to fields of natural language processing and deep learning technologies. A specific implementation solution includes: performing a feature extraction on source sample text data to obtain a sample feature vector sequence; obtaining a target sample feature vector according to the sample feature vector sequence; performing an autoregressive decoding and a non-autoregressive decoding on the sample feature vector sequence, respectively; performing a length prediction on the target sample feature vector; training a predetermined model by using translation sample data, the autoregressive text translation result, the non-autoregressive text translation result, a true length value of the source sample text, the first predicted length value, a true length value of the translation sample text, and the second predicted length value to obtain the text translation model.

Training method, text translation method, electronic device, and storage medium

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.

Display method, electronic device, and storage medium

A text processing method is provided. The method includes: a first probability value of each candidate character of a plurality of candidate characters corresponding to a target position is determined based on character feature information corresponding to the target position in a text fragment to be processed, wherein the character feature information is determined based on a context at the target position in the text fragment to be processed; a second probability value of each candidate character of the plurality of candidate characters is determined based on a character string including the candidate character and at least one character in at least one position in the text fragment to be processed adjacent to the target position; and a correction character at the target position is determined based on the first probability value and the second probability value of each candidate character of the plurality of candidate characters.

Text processing method

Backlight module and display device are provided. Backlight module is for providing light source for display panel. Display panel has bonding side at a side of display panel in first direction. Backlight module includes: back plate, including base plate at backlight side of display panel, and first side plate at bonding side, where a side of first side plate away from base plate is bent towards direction away from center of base plate to form top plate supporting display panel; rubber frame, including second side plate at bonding side, where first opening is in middle of second side plate in extension direction of second side plate to accommodate first side plate; main circuit board, including opposite first and second ends in first direction, where first end is inserted between top plate and first side plate, and second end has first bonding area for bonding connection with display panel.

Backlight module and display device

A translation method, a model training method, apparatuses, electronic devices and storage mediums, which relate to the field of artificial intelligence technologies, such as machine learning technologies, information processing technologies, are disclosed. In an implementation, a weight for each translation model in at least two pre-trained translation models translating a to-be-translated specified sentence is acquired based on the specified sentence and a pre-trained weighting model; and the specified sentence is translating using the at least two translation models based on the weight for each translation model translating the specified sentence.

Translation method, model training method, electronic devices and storage mediums

The present disclosure provides a translation method and apparatus, an electronic device, and a non-transitory storage medium. An implementation includes: determining an encoded feature of a sentence to be translated by an encoding module; determining, by a graph network module, a knowledge fusion feature of the sentence to be translated based on a preset graph network, wherein the preset graph network is constructed based on a polysemous word in a source language corresponding to the sentence to be translated and a plurality of translated words corresponding to the polysemous word in a target language; determining, by a decoding network, a translated sentence corresponding to the sentence to be translated based on the encoded feature and the knowledge fusion feature.

Translation method, apparatus and storage medium

A translation method, an electronic device and a storage medium, which relate to the field of artificial intelligence technologies, such as machine learning technologies, information processing technologies, are disclosed. An implementation includes: acquiring an intermediate translation result generated by each of multiple pre-trained translation models for a to-be-translated specified sentence in a same iteration of a translation process, so as to obtain multiple intermediate translation results; acquiring a co-occurrence word based on the multiple intermediate translation results; and acquiring a target translation result of the specified sentence based on the co-occurrence word.

Translation method, electronic device and storage medium

Growing community of inventors

Beijing, China

Zhi Li