公开(公告)号：US11687718B2

公开(公告)日：2023-06-27

申请号：US17116846

申请日：2020-12-09

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Chao Pang ,  Shuohuan Wang ,  Yu Sun ,  Hua Wu ,  Haifeng Wang

IPC: G06F17/00 ,  G06F40/295 ,  G06F40/137 ,  G06F40/30

CPC classification number: G06F40/295 ,  G06F40/137 ,  G06F40/30

Abstract: A method, an apparatus, a device and a storage medium for learning a knowledge representation are provided. The method can include: sampling a sub-graph of a knowledge graph from a knowledge base; serializing the sub-graph of the knowledge graph to obtain a serialized text; and reading using a pre-trained language model the serialized text in an order in the sub-graph of the knowledge graph, to perform learning to obtain a knowledge representation of each word in the serialized text. The knowledge representation learning in this embodiment is performed for entity and relationship representation learning in the knowledge base.

公开(公告)号：US11562150B2

公开(公告)日：2023-01-24

申请号：US17031569

申请日：2020-09-24

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Han Zhang ,  Dongling Xiao ,  Yukun Li ,  Yu Sun ,  Hao Tian ,  Hua Wu ,  Haifeng Wang

IPC: G06F17/00 ,  G06F40/56

Abstract: The present disclosure proposes a language generation method and apparatus. The method includes: performing encoding processing on an input sequence by using a preset encoder to generate a hidden state vector corresponding to the input sequence; in response to a granularity category of a second target segment being a phrase, decoding a first target segment vector, the hidden state vector, and a position vector corresponding to the second target segment by using N decoders to generate N second target segments; determining a loss value based on differences between respective N second target segments and a second target annotated segment; and performing parameter updating on the preset encoder, a preset classifier, and the N decoders based on the loss value to generate an updated language generation model for performing language generation.

公开(公告)号：US11520991B2

公开(公告)日：2022-12-06

申请号：US16885358

申请日：2020-05-28

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Yu Sun ,  Haifeng Wang ,  Shuohuan Wang ,  Yukun Li ,  Shikun Feng ,  Hao Tian ,  Hua Wu

IPC: G06F40/30 ,  G06F40/40

Abstract: The present disclosure provides a method, apparatus, electronic device and storage medium for processing a semantic representation model, and relates to the field of artificial intelligence technologies. A specific implementation solution is: collecting a training corpus set including a plurality of training corpuses; training the semantic representation model using the training corpus set based on at least one of lexicon, grammar and semantics. In the present disclosure, by building the unsupervised or weakly-supervised training task at three different levels, namely, lexicon, grammar and semantics, the semantic representation model is enabled to learn knowledge at levels of lexicon, grammar and semantics from massive data, enhance the capability of universal semantic representation and improve the processing effect of the NLP task.

公开(公告)号：US11275904B2

公开(公告)日：2022-03-15

申请号：US16868426

申请日：2020-05-06

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Ruiqing Zhang ,  Chuanqiang Zhang ,  Hao Xiong ,  Zhongjun He ,  Hua Wu ,  Zhi Li ,  Haifeng Wang

IPC: G06F17/00 ,  G06F40/40

Abstract: Embodiments of the present disclosure provide a method and an apparatus for translating a polysemy, and a medium. The method includes: obtaining a source language text; identifying and obtaining the polysemy from the source language text; inquiring related words corresponding to each interpretation of the polysemy; determining a target interpretation corresponding to the related words contained in the source language text; and translating the polysemy into the target interpretation.

公开(公告)号：US20210234814A1

公开(公告)日：2021-07-29

申请号：US17208865

申请日：2021-03-22

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Hua Wu ,  Haifeng Wang ,  Zhanyi Liu

IPC: H04L12/58 ,  G06N3/02 ,  G06N5/02 ,  G06K9/62

Abstract: A method for human-machine interaction based on a neural network is provided. The method includes: providing a user input as a first input for a neural network system; providing the user input to a conversation control system different from the neural network system; processing the user input by the conversation control system based on information relevant to the user input; providing a processing result of the conversation control system as second input for the neural network system; and generating, by the neural network system, a reply to the user input based on the first and second input.

公开(公告)号：US10902077B2

公开(公告)日：2021-01-26

申请号：US16313195

申请日：2016-09-05

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Yanjun Ma ,  Jiachen Liu ,  Hua Wu

IPC: G06F16/30 ,  G06F16/9535 ,  G06F16/953 ,  G06F16/2458 ,  G06N20/00 ,  G06F16/9538

Abstract: The present disclosure provides a search result aggregation method and apparatus based on artificial intelligence and a search engine. The method includes: obtaining a query; generating a plurality of search results according to the query; obtaining a plurality of corresponding demand dimensions according to the query; aggregating the plurality of demand dimensions according to the plurality of search results; obtaining an answer corresponding to each demand dimension, and aggregating the answers corresponding to the plurality of demand dimensions according to the aggregated demand dimensions to generate an aggregation result.

公开(公告)号：US10467349B2

公开(公告)日：2019-11-05

申请号：US15832013

申请日：2017-12-05

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Zhongjun He ,  Hongyu Liu ,  Shiqi Zhao ,  Hua Wu

IPC: G06F17/00 ,  G06F3/00 ,  G06F17/28 ,  G06N3/02 ,  G06N3/04 ,  G06N3/08

Abstract: The resent disclosure provides a method and an apparatus for translating based on artificial intelligence. With the method, the text to be translated from the source language to the target language is acquired, in which, the text includes the target language term and the source language term. The candidate terms for translating the source language term and confidences of the candidate terms are determined. The candidate terms are used to replace the corresponding source language term, and each candidate term is combined with the target language term, so as to obtain each candidate translation. A probability of forming a smooth text when the candidate term is used in the candidate translation is predicted. Then the target term is chosen to be recommended according to the language probabilities of the candidate translations and the confidences of the candidate terms.

公开(公告)号：US09953024B2

公开(公告)日：2018-04-24

申请号：US14892933

申请日：2014-09-04

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xiaoning Zhu ,  Zhongjun He ,  Hua Wu ,  Haifeng Wang

IPC: G06F17/21 ,  G06F17/27 ,  G06F17/28 ,  G06F17/20 ,  G10L21/00 ,  G06F17/30

CPC classification number: G06F17/2735 ,  G06F17/2827 ,  G06F17/2845 ,  G06F17/3043 ,  G06F17/30489 ,  G06F17/30654 ,  G06F17/30669

Abstract: Disclosed are a method and a device for expanding data of a bilingual corpus. The method for expanding data of a bilingual corpus includes: searching, in a source language-pivot language corpus, for at least one first pivot language phrase semantically matching a first source language phrase; searching, in the source language-pivot language corpus, for at least one second source language phrase semantically matching each of the first pivot language phrases to form a source language phrase set by the second source language phrases; searching, in a pivot language-target language corpus, for at least one first target language phrase semantically matching each of the first pivot language phrases to form a target language phrase set by the first target language phrases; combining the second source language phrases in the source language phrase set with the first target language phrases in the target language phrase set, so as to form at least one phrase pair in which a source language phrase and a target language phrase semantically match; and storing the formed at least one phrase pair in which the source language phrase and the target language phrase semantically match into a source language-target language corpus. Data in a bilingual corpus is expanded, so that the problem of data sparseness in the bilingual corpus is solved.

公开(公告)号：US20160239481A1

公开(公告)日：2016-08-18

申请号：US14892933

申请日：2014-09-04

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xiaoning Zhu ,  Zhongjun He ,  Hua Wu ,  Haifeng Wang

IPC: G06F17/27 ,  G06F17/30 ,  G06F17/28

CPC classification number: G06F17/2735 ,  G06F17/2827 ,  G06F17/2845 ,  G06F17/3043 ,  G06F17/30489 ,  G06F17/30654 ,  G06F17/30669

Abstract: Disclosed are a method and a device for expanding data of a bilingual corpus. The method for expanding data of a bilingual corpus includes: searching, in a source language-pivot language corpus, for at least one first pivot language phrase semantically matching a first source language phrase; searching, in the source language-pivot language corpus, for at least one second source language phrase semantically matching each of the first pivot language phrases to form a source language phrase set by the second source language phrases; searching, in a pivot language-target language corpus, for at least one first target language phrase semantically matching each of the first pivot language phrases to form a target language phrase set by the first target language phrases; combining the second source language phrases in the source language phrase set with the first target language phrases in the target language phrase set, so as to form at least one phrase pair in which a source language phrase and a target language phrase semantically match; and storing the formed at least one phrase pair in which the source language phrase and the target language phrase semantically match into a source language-target language corpus. Data in a bilingual corpus is expanded, so that the problem of data sparseness in the bilingual corpus is solved.

Abstract translation: 公开了一种用于扩展双语语料库数据的方法和装置。 用于扩展双语语料库的数据的方法包括：在源语言 - 枢轴语言语料库中搜索语义上匹配第一源语言短语的至少一个第一枢轴语言短语; 在源语言 - 枢轴语言语料库中搜索至少一个第二源语言短语，语义上匹配每个第一枢轴语言短语以形成由第二源语言短语设置的源语言短语; 在枢轴语言目标语言语料库中搜索至少一个第一目标语言短语，语义上匹配每个第一枢轴语言短语以形成由第一目标语言短语设置的目标语言短语; 将源语言短语集合中的第二源语言短语与目标语言短语集合中的第一目标语言短语组合，以形成源语言短语和目标语言短语在语义上匹配的至少一个短语对; 并且将所形成的至少一个短语对存储在源语言短语和目标语言短语语义匹配中到源语言目标语言语料库中。 双语语料库中的数据扩展，双语语料库数据稀疏问题得到解决。

公开(公告)号：US20160147744A1

公开(公告)日：2016-05-26

申请号：US14893008

申请日：2014-11-12

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Haifeng Wang ,  Hua Wu

IPC: G06F17/28 ,  G10L15/01 ,  G10L15/00

CPC classification number: G06F17/2854 ,  G06F17/2845 ,  G06F17/289 ,  G10L15/005 ,  G10L15/01

Abstract: Disclosed are on-line voice translation method and device. The method comprises: conducting voice recognition on first voice information input by a first user, so as to obtain first recognition information; prompting the first user to confirm the first recognition information; translating the confirmed first recognition information to obtain and output first translation information; extracting, according to second information which is fed back by a second user, associated information corresponding to the second information; and correcting the first translation information according to the associated information and outputting the corrected translation information. By means of the on-line voice translation method and device, smooth communication can be ensured in cross-language exchanges.

Abstract translation: 披露了在线语音翻译方法和设备。 该方法包括：对由第一用户输入的第一语音信息进行语音识别，以获得第一识别信息; 提示第一用户确认第一识别信息; 翻译确认的第一识别信息以获得和输出第一翻译信息; 根据由第二用户反馈的第二信息，提取与第二信息相对应的相关信息; 以及根据所述关联信息来校正所述第一翻译信息并输出所述经修正的翻译信息。 通过在线语音翻译方法和设备，可以在跨语言交换中保证顺畅的沟通。