公开(公告)号：US11562123B2

公开(公告)日：2023-01-24

申请号：US17215068

申请日：2021-03-29

申请人： Yixuan Tong ,  Yongwei Zhang ,  Bin Dong ,  Shanshan Jiang ,  Jiashi Zhang

发明人： Yixuan Tong ,  Yongwei Zhang ,  Bin Dong ,  Shanshan Jiang ,  Jiashi Zhang

IPC分类号： G06F40/166 ,  G06K9/62 ,  G06N3/08

摘要： A method and an apparatus for fusing position information, and a non-transitory computer-readable recording medium are provided. In the method, words of an input sentence are segmented to obtain a first sequence of words in the input sentence, and absolute position information of the words in the first sequence is generated. Then, subwords of the words in the first sequence are segmented to obtain a second sequence including subwords, and position information of the subwords in the second sequence are generated, based on the absolute position information of the words in the first sequence, to which the respective subwords belong. Then, the position information of the subwords in the second sequence are fused into a self-attention model to perform model training or model prediction.

公开(公告)号：US20220164536A1

公开(公告)日：2022-05-26

申请号：US17455967

申请日：2021-11-22

申请人： Yixuan TONG ,  Yongwei ZHANG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

发明人： Yixuan TONG ,  Yongwei ZHANG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

IPC分类号： G06F40/295

摘要： A method and an apparatus for sequence labeling on an entity text, and a non-transitory computer-readable recording medium are provided. In the method, a start position of an entity text within a target text is determined. Then, a first matrix is generated based on the start position of the entity text. Elements in the first matrix indicates focusable weights of each word with respect to other words in the target text. Then, a named entity recognition model is generated using the first matrix. The named entity recognition model is obtained by training using first training data, the first training data includes word embeddings corresponding to respective texts in a training text set, and the texts are texts whose entity label has been labeled. Then, the target text is input to the named entity recognition model, and probability distribution of the entity label is output.

公开(公告)号：US11270212B2

公开(公告)日：2022-03-08

申请号：US15919355

申请日：2018-03-13

申请人： Lei Ding ,  Yixuan Tong ,  Bin Dong ,  Shanshan Jiang ,  Yongwei Zhang

发明人： Lei Ding ,  Yixuan Tong ,  Bin Dong ,  Shanshan Jiang ,  Yongwei Zhang

IPC分类号： G06N5/02 ,  G06N3/04 ,  G06N3/08 ,  G06F16/28 ,  G06F16/31 ,  G06F16/951 ,  G06F16/22 ,  G06F16/901 ,  G06F40/279 ,  G06F40/295

摘要： Knowledge graph processing method and device are disclosed. The method includes steps of obtaining an entity set containing a first entity, a second entity, and relation information; acquiring text information and image information related to the first entity and the second entity; generating a first structural information vector of the first entity and a second structural information vector of the second entity, and creating a first text information vector of the first entity, a first image information vector of the first entity, a second text information vector of the second entity, and a second image information vector of the second entity; and building a joint loss function so as to attain a first target vector of the first entity, a second target vector of the second entity, and a target relation vector of the relation information between the first entity and the second entity.

公开(公告)号：US20210390454A1

公开(公告)日：2021-12-16

申请号：US17343955

申请日：2021-06-10

申请人： Tianxiong XIAO ,  Yixuan TONG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

发明人： Tianxiong XIAO ,  Yixuan TONG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

IPC分类号： G06N20/00 ,  G06F40/20 ,  G06K9/62

摘要： Disclosed is an apparatus for training a machine reading comprehension model. The apparatus is inclusive of a distance calculation part configured to calculate, based on a position of each word within a training text and a position of an answer label within the training text, a distance between the same word and the answer label; a label smoothing part configured to input the distance between the same word and the answer label into a smooth function to obtain a probability value corresponding to the same word, outputted from the smooth function; and a model training part configured to make the probability value corresponding to the same word serve as a smoothed label of the same word so as to train the machine reading comprehension model.

公开(公告)号：US10971136B2

公开(公告)日：2021-04-06

申请号：US16218693

申请日：2018-12-13

申请人： Yihan Li ,  Yixuan Tong ,  Shanshan Jiang ,  Bin Dong

发明人： Yihan Li ,  Yixuan Tong ,  Shanshan Jiang ,  Bin Dong

IPC分类号： G10L15/18 ,  G06F16/33 ,  G10L15/14 ,  G10L15/06 ,  G06F40/30 ,  G06F40/35 ,  G06F40/56 ,  G06F40/216 ,  G10L15/22

摘要： A method and an apparatus for ranking responses of a dialog model, and a non-transitory computer-readable recording medium are provided. The dialog model is trained based on a sample data set. The method includes obtaining, from the sample data set, at least one similar dialog whose content is semantically similar to content of a target dialog; obtaining a probability of at least one target response generated by the dialog model when inputting the target dialog, and obtaining a probability of a target response generated by the dialog model when inputting the similar dialog; statistically analyzing, based on the probabilities of the respective generated target responses, scores of the target responses, the scores of the target responses being positively correlated with the probabilities of the target responses; and ranking the target responses in a descending order of the scores.

公开(公告)号：US20210081788A1

公开(公告)日：2021-03-18

申请号：US17015560

申请日：2020-09-09

申请人： Lei DING ,  Yixuan TONG ,  Jiashi ZHANG ,  Shanshan JIANG ,  Yongwei ZHANG

发明人： Lei DING ,  Yixuan TONG ,  Jiashi ZHANG ,  Shanshan JIANG ,  Yongwei ZHANG

IPC分类号： G06N3/08 ,  G06N7/00

摘要： A method and an apparatus for generating sample data, and a non-transitory computer-readable recording medium are provided. In the method, at least two weak supervision recommendation models of a recommendation system are generated; a dependency relation between the at least two weak supervision recommendation models is learned by training a neural network model; and the sample data is re-labelled using the trained neural network model to obtain updated sample data.

公开(公告)号：US20200242486A1

公开(公告)日：2020-07-30

申请号：US16739311

申请日：2020-01-10

申请人： Liang LIANG ,  Lei Ding ,  Bin Dong ,  Shanshan Jiang ,  Yixuan Tong

发明人： Liang LIANG ,  Lei Ding ,  Bin Dong ,  Shanshan Jiang ,  Yixuan Tong

IPC分类号： G06N5/02 ,  G06K9/62 ,  G06N20/10 ,  G06F16/9032

摘要： A method and an apparatus for recognizing an intention, and a non-transitory computer-readable recording medium are provided. The method includes learning vectors of knowledge base elements in corpus samples, and converting the corpus samples into row vectors composed of the vectors of the knowledge base elements in a knowledge base; extracting feature vectors from respective pooling windows in the corpus samples by hierarchical pooling, determining weights positively correlated with similarities between texts within the respective pooling windows and the respective corpus samples, performing weighting on the extracted feature vectors to obtain feature vectors of the respective pooling windows, and obtaining feature vectors of the respective corpus samples composed of the feature vectors of the pooling windows; training a vector-based intention recognition classifier, based on the feature vectors of the corpus samples; and recognizing an intention in querying a corpus, using the trained intention recognition classifier.

公开(公告)号：US20240338523A1

公开(公告)日：2024-10-10

申请号：US18623332

申请日：2024-04-01

申请人： Yuming ZHANG ,  Bin Dong ,  Shanshan Jiang ,  Yongwei Zhang

发明人： Yuming ZHANG ,  Bin Dong ,  Shanshan Jiang ,  Yongwei Zhang

IPC分类号： G06F40/295 ,  G06F40/284 ,  G06N20/00

CPC分类号： G06F40/295 ,  G06F40/284 ,  G06N20/00

摘要： A method and an apparatus are provided for training a named entity recognition (NER) model. By constructing tag annotations for tags and causing the tag annotations to contain information for indicating the positions of tokens in named entities, corresponding to the tags, respectively, in the process of training the NER model, the NER model can better understand the different positions of different tokens in the same named entity, so that the trained NER model can more accurately recognize named entities.

公开(公告)号：US11907661B2

公开(公告)日：2024-02-20

申请号：US17455967

申请日：2021-11-22

申请人： Yixuan Tong ,  Yongwei Zhang ,  Bin Dong ,  Shanshan Jiang ,  Jiashi Zhang

发明人： Yixuan Tong ,  Yongwei Zhang ,  Bin Dong ,  Shanshan Jiang ,  Jiashi Zhang

IPC分类号： G06F40/279 ,  G06F40/295

CPC分类号： G06F40/295

摘要： A method and an apparatus for sequence labeling on an entity text, and a non-transitory computer-readable recording medium are provided. In the method, a start position of an entity text within a target text is determined. Then, a first matrix is generated based on the start position of the entity text. Elements in the first matrix indicates focusable weights of each word with respect to other words in the target text. Then, a named entity recognition model is generated using the first matrix. The named entity recognition model is obtained by training using first training data, the first training data includes word embeddings corresponding to respective texts in a training text set, and the texts are texts whose entity label has been labeled. Then, the target text is input to the named entity recognition model, and probability distribution of the entity label is output.

公开(公告)号：US20230394240A1

公开(公告)日：2023-12-07

申请号：US18326292

申请日：2023-05-31

申请人： Yongwei ZHANG ,  Bin Dong ,  Shanshan Jiang ,  Lei Ding ,  Jiashi Zhang

发明人： Yongwei ZHANG ,  Bin Dong ,  Shanshan Jiang ,  Lei Ding ,  Jiashi Zhang

IPC分类号： G06F40/295 ,  G06F40/40

CPC分类号： G06F40/295 ,  G06F40/40

摘要： A method and an apparatus for named entity recognition, and a non-transitory computer-readable recording medium are provided. In the method, text elements are traversed according to a text span to obtain candidate entity words. Then, a class to which the candidate entity word belongs is recognized. The recognizing of the class includes generating a prompt template corresponding to the candidate entity word, and concatenating the text to be recognized and the prompt template to obtain a concatenated text; generating vector representations of the text elements in the concatenated text; generating the vector representation of the candidate entity word according to the vector representations of the text elements of each candidate entity word in the concatenated text, and the vector representation of the text element of the mask word; and classifying the vector representation of the candidate entity word to obtain the class of the candidate entity word.