Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Baidu Online Network Technology Co., Ltd.

Tingting Li

Shuqi Sun

Zhenyu Jiao

Yue Chang

Ke Wei Sun

Lijie Wang

Xinyan Xiao

Shiqi Zhao

Hongjie Guo

Hongyang Zhang

Huifeng Sun

Haifeng Wang

Hua Wu

Lei Han

Bo Yu

Shuai Zhang

Hao Li

Chaoyue Wang

Wei Wan

Ao Zhang

Hehan Li

Xiangyang Zhou

Weijie Ren

Jianglu Hu

Zhenlong Yu

Liansheng Sun

A method for processing a question is performed by an electronic device. The method includes: receiving a question to be processed from a user input; determining a first similarity between the question to be processed and each candidate question in at least one reference question-answer (Q&A) pair; determining a second similarity between the question to be processed and the at least one reference Q&A pair based on the first similarity; determining a target Q&A pair from the at least one reference Q&A pair based on the second similarity; and replying to the user for the question to be processed based on a target answer in the target Q&A pair.

Method for processing question, electronic device and storage medium

A model training method, a method and an apparatus for human-machine interaction. The method includes: acquiring a sample set corresponding to a template; constructing positive example pairs and negative example pairs for a contrastive learning task based on the sample set; performing contrastive learning training on a pre-training model based on the positive example pairs and the negative example pairs for the contrastive learning task.

Model training method and method for human-machine interaction

The present application discloses a method and an apparatus for generating a dialogue, and a storage medium. The method includes: obtaining problem information; inputting the problem information to a small sample learning model to generate a first feature; inputting the problem information to a deep learning (DL) model to generate a second feature; combining the first feature and the second feature to generate a feature sequence; and inputting the feature sequence to a fusion model to generate dialogue information corresponding to the problem information.

Method and apparatus for creating dialogue, and storage medium

A semantic understanding method, includes: acquiring a query statement and a preceding dialogue; rewriting the query statement based on a preset rule to generate a target query statement if it is recognized that the query statement meets a rule rewriting condition according to the query statement and the preceding dialogue; rewriting the query statement based on a rewriting model to generate the target query statement if it is recognized that the query statement does not meet the rule rewriting condition according to the query statement and the preceding dialogue; and performing intention recognition according to the target query statement to generate an intention recognition result.

Semantic understanding method, electronic device, and storage medium

The disclosure provides a method for generating a dialogue. The method includes: obtaining an input sentence; determining a type of a task-based response sentence that is to be generated, by updating a current dialogue state based on the input sentence; generating the task-based response sentence by inputting the input sentence into a task-based dialogue response generator; and determining the task-based response sentence as a target response sentence in response to the type of the task-based response sentence being a designated type.

Method for generating dialogue, electronic device, and storage medium

The disclosure provides a method for generating a query statement. The method includes: determining a first vector representation based on known nodes in a first syntax tree corresponding to a query statement to be generated; determining a target generation strategy corresponding to a target node to be generated based on the first vector representation and a preset copy reference matrix; generating the target node based on the first vector representation or a second vector representation by performing the target generation strategy, in which the second vector representation is a vector representation corresponding to an adjacent query statement prior to the query statement to be generated; and generating the query statement based on the known nodes and a terminator in response to the target node being the terminator.

Method for generating query statement, electronic device and storage medium

A method for recognizing a dialogue intention, an electronic device and a storage medium are provided. The solution includes: obtaining a sample sentence with an intention category to be predicted and a plurality of supporting sentences each labeled with an intention category; and inputting the sample sentence and the plurality of supporting sentences into a trained intention recognition model, in which the trained intention recognition model is configured to generate a sample sentence vector corresponding to the sample sentence and category vectors corresponding to the plurality of supporting sentences based on the sample sentence and the plurality of supporting sentences, calculate matching degrees between the sample sentence vector and the category vectors, and obtain a predicted intention category of the sample sentence based on the matching degrees.

Method for recognizing dialogue intention, electronic device and storage medium

The present disclosure provides a method and apparatus for acquiring a pre-trained model, an electronic device and a storage medium, and relates to the field of artificial intelligence, such as the natural language processing field, the deep learning field, or the like. The method may include: adding, in a process of training a pre-trained model using training sentences, a learning objective corresponding to syntactic information for a self-attention module in the pre-trained model; and training the pre-trained model according to the defined learning objective. The solution of the present disclosure may improve a performance of the pre-trained model, and reduce consumption of computing resources, or the like.

Method and apparatus for acquiring pre-trained model, electronic device and storage medium

Embodiments of the present disclosure provide a method and apparatus for outputting analysis abnormality information in a spoken language understanding. The method includes: acquiring first spoken language information and a first analysis result for the first spoken language information; determining whether the first analysis result includes intent information; determining whether the first spoken language information includes a predefined word slot value, in response to determining the first analysis result not including the intent information; and outputting information indicating an existence of an abnormality in the first analysis result, in response to determining the first spoken language information including the predefined word slot value.

Method and apparatus for outputting analysis abnormality information in spoken language understanding

Embodiments of the present disclosure provide a method and apparatus for outputting a structured query sentence. The method may include: acquiring a to-be-converted natural language sentence; inputting the to-be-converted natural language sentence into a pre-trained sequence to sequence model to obtain an action sequence corresponding to the to-be-converted natural language sentence; generating a directed acyclic graph according to the action sequence; and outputting a structured query sentence corresponding to the generated directed acyclic graph according to a preset corresponding relationship between a directed acyclic graph and a structured query sentence.

Method and apparatus for outputting structured query sentence

The present disclosure discloses a method for generating a question answering robot, relates to the field of robotics. The specific implementation includes: obtaining field information input by a user, obtaining a field-specific robot from a robot library based on the field information; obtaining a template list corresponding to the field-specific robot, providing the template list to the user, the template list including a plurality of templates; receiving the plurality of templates filled in by the user, the templates filled in by the user including at least one question and an answer corresponding to the at least one question; expanding the at least one question filled in by the user based on a question semantic database to form a combination of questions corresponding to the answer, the answer and the combination of questions forming a question-answer pair; and generating a question answering robot based on the question-answer pair.

Method for generating question answering robot and computer device

The present disclosure provides a synonym tag obtaining method and apparatus, a device, and a computer readable storage medium. By obtaining the central morpheme of the tag to be recognized and then obtaining the tag template of the tag to be recognized according to the tag to be recognized and the central morpheme of the tag to be recognized, to obtain the synonymy tag of the tag to be recognized according to the tag template, and the central morpheme of the tag to be recognized and at least one cluster of synonymy tag templates, it is possible to avoid the technical problem about reduction of the coverage rate of the synonymy tags caused by data sparsity of the mining resources and thereby improve the reliability of obtaining synonymy tags, without depending on mining resources such as a click log having a paraphrase relationship or data having bilingual parallel alignment corpus.

Synonymy tag obtaining method and apparatus, device and computer readable storage medium

An information searching method and an information searching device are provided. The information searching method includes: receiving, at one or more computing devices, a first query from a client device, and obtaining, at the one or more computing devices an intention clarification guidance sentence according to the first query; receiving a second query updated according to the intention clarification guidance sentence; obtaining a search result according to the second query; and returning the search result to the client device.

Growing community of inventors

Beijing, China

Tingting Li