Beijing Baidu Netcom Science And Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Beijing Xiaomi Mobile Software Co., Ltd.

Baidu Online Network Technology (Beijing) Co., Ltd.

Other

Microsoft Technology Licensing, LLC

Kabushiki Kaisha Toshiba

Baidu USA LLC

Sinovet (Beijing) Biotechnology Co., Ltd.

Hua Wu

Haifeng Wang

Zhongjun He

Ruiqing Zhang

Yu Sun

Zhi Li

Hao Tian

Hao Xiong

Shuohuan Wang

Chuanqiang Zhang

Jing Liu

Yong Zhu

Zhi Hong Li

Wenbin Jiang

Zhanyi Liu

Xiyang Wang

Ming Zhou

Hui Liu

Xinyan Xiao

Yajuan Lyu

Chao Pang

Baoqiu Cui

Fan Wang

Tian Wu

Jingzhou He

Yukun Li

Chang-Ning Huang

Jiachen Liu

Siyu Ding

Siqi Bao

Yingqi Qu

Wei Li

Jianfeng Gao

Han Zhang

Yue Hua Zhang

Yanjun Ma

Qiaoqiao She

Hongguang Dong

Hongyu Li

Shikun Feng

Shuangshuang Cui

Yongzheng Xin

Junyuan Shang

Dongling Xiao

Yuchen Ding

Huang He

Zhengyu Niu

Yanbin Zhao

Fengtao Huang

Jingxuan Zhao

Xuan Ouyang

Xing Wan

Hongwei Fan

Ruiduan Wang

Kai Liu

Jun Xu

Xin Wang

Quan Wang

Qian Xu

Fei Yu

Shiqi Zhao

Xiaoguang Hu

Junjie Li

Hongyu Liu

Tingting Li

Shuqi Sun

Kun Jing

Pingping Huang

Jian Li

Xing Li

Junjie Dong

Bo Yang

Yue Chang

Yajuan Lv

Xingjian Li

Zhou Xin

Weimeng Zhang

Xingfei Ge

Zhe Hu

Hairong Liu

Jialin Li

Guocheng Niu

Daisong Guan

Jian Gong

Jiaxiang Liu

Hehan Li

Haojie Wei

Guohua Li

Huifeng Sun

Xinchao Xu

Can Gao

Mingbo Ma

Zeyang Lei

Weichong Yin

Liang Huang

Renjie Zheng

Meng Liao

Xingwu Sun

Ming Zong

Xijuan Zhang

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 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 method is provided. The method includes converting a search request of a user into a first request semantic vector. The method further includes searching a search resource database for at least one first data semantic vector matched with the first request semantic vector, wherein the search resource database is constructed as a semantic vector space in which different types of data are converted into corresponding data semantic vectors, and the different types of data include at least texts, pictures and videos. The method further includes generating, based on the at least one first data semantic vector, a search result.

Search method, computing device and storage medium

An information search method includes: obtaining search words at least including a question to be searched and obtaining an initial text vector representation of the search words; obtaining a video corresponding to the search words, and obtaining multi-modality vector representations of the video; starting from the initial text vector representation, performing N rounds of interaction between the video and the search words based on the multi-modality vector representations and a text vector representation of the search words of a current round, to generate a target fusion vector representation, where N is an integer greater than or equal to 1; and obtaining target video frames matching the question to be searched by annotating the video based on the target fusion vector representation.

Information search method and device, electronic device, and storage medium

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 method for pre-training a language model includes: constructing a pre-training language data set, in which the pre-training language data set comprises unsupervised language data and supervised language data; generating a hierarchical multi-template and multi-task language data set based on the pre-training language data set; and pre-training the language model based on the hierarchical multi-template and multi-task language data set.

Method for pre-training language model

The present disclosure discloses a method for acquiring a structured question-answering (QA) model, a QA method and corresponding apparatuses, and relates to knowledge graph and deep learning technologies in the field of artificial intelligence technologies. A specific implementation solution involves: acquiring training samples corresponding to N structured QA database types, the training samples including question samples, information of the structured QA database types and query instruction samples used by the question samples to query structured QA databases of the types, N being an integer greater than 1; and training a text generation model by using the training samples to obtain the structured QA model, wherein the question samples and the information of the structured QA database types are taken as input to the text generation model, and the query instruction samples are taken as target output of the text generation model.

Method for acquiring structured question-answering model, question-answering method and corresponding apparatus

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 method for training a document reading comprehension model includes: acquiring a question sample and a rich-text document sample, in which the rich-text document sample includes a real answer of the question sample; acquiring text information and layout information of the rich-text document sample by performing OCR processing on image information of the rich-text document sample; acquiring a predicted answer of the question sample by inputting the text information, the layout information and the image information of the rich-text document sample into a preset reading comprehension model; and training the reading comprehension model based on the real answer and the predicted answer. The method may enhance comprehension ability of the reading comprehension model to the long rich-text document, and save labor cost.

Method and device for training, based on crossmodal information, document reading comprehension model

The disclosure provides a method for training a semantic retrieval network, an electronic device and a storage medium. The method includes: obtaining a training sample including a search term and n candidate files corresponding to the search term, where n is an integer greater than 1; inputting the training sample into the ranking model, to obtain n first correlation degrees output by the ranking model, in which each first correlation degree represents a correlation between a candidate document and the search term; inputting the training sample into the semantic retrieval model, to obtain n second correlation degrees output by the semantic retrieval model, wherein each second correlation degree represents a correlation between a candidate document and the search term; and training the semantic retrieval model and the ranking model jointly based on the n first correlation degrees and the n second correlation degrees.

Method and apparatus for training semantic retrieval network, 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

The present disclosure discloses a method and apparatus for acquiring a pre-trained model, and relates to natural language processing and deep learning technologies in the field of artificial intelligence technologies. An implementation includes: acquiring training data, the training data including a single-modal language material and a multi-modal language material, and the multi-modal language material including a language material pair formed by a first-modal language material and a second-modal language material; and performing a multi-task training operation on a pre-trained model using the training data, the multi-task including at least one cross-modal contrastive learning task and at least one single-modal learning task; the pre-trained language model obtained in the present disclosure may learn from different forms of language materials, i.e., the single-modal language material and the multi-modal language material, such that the pre-trained language model may effectively process information in various modals.

Method and apparatus for acquiring pre-trained model

A model training method, a model training platform, an electronic device and a storage medium are provided, which can be used in the field of artificial intelligence, particularly the fields of natural language processing and deep learning. The model training method includes: receiving an input; determining, based on the input, a user-oriented prefabricated function; determining, based on the input, a model training function; determining, based on the input, a pre-trained model; determining, based on the input, a network structure associated with the pre-trained model so as to support use of the pre-trained model; training, based on the input, the model by using the prefabricated function, the model training function, and the pre-trained model; and providing an output associated with a trained model.

Model training

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

Growing community of inventors

Beijing, China

Hua Wu