-
公开(公告)号：US20220245000A1
公开(公告)日：2022-08-04
申请号：US17162069
申请日：2021-01-29
发明人： Anup Kalia , Changhua Sun , HongLei Guo , Zhili Guo , Zhong Su , Jin Xiao , Maja Vukovic , Shawn Dsouza
摘要： Systems, computer-implemented methods, and computer program products to facilitate modernization of an application are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a determination component that determines one or more relevant surrounding contexts for a raw entity. The computer executable components also can comprise a matching component that matches the one or more relevant surrounding contexts with one or more known surrounding contexts of one or more known entities. The computer executable components further can comprise a type identification component that identifies an entity type for the raw entity based on the matching of the one or more relevant surrounding contexts with the one or more known surrounding contexts.
-
公开(公告)号：US20220012919A1
公开(公告)日：2022-01-13
申请号：US16923142
申请日：2020-07-08
发明人： Shiwan Zhao , Yi Ke Wu , Hao Kai Zhang , Zhong Su
摘要： In an approach to improving the image captioning performance of low-resource languages by leveraging multimodal inputs, one or more computer processors encode an image utilizing an image encoder, wherein the image is contained within a triplet comprising the image, one or more high-resource captions, and one or more low-resource captions. The one or more computer processors generate one or more high-resource captions utilizing the encoded image and the triplet inputted into a high-resource decoder. The one or more computer processors encode the one or more generated high-resource captions utilizing a high-resource encoder. The one or more computer processors add adaptive cycle consistency constraints on a set of calculated attention weights associated the triplet. The one or more computer processors generate one or more low-resource captions by simultaneously inputting the encoded image, the encoded high-resource caption, and the triplet into a trained low-resource decoder.
-
公开(公告)号：US11176333B2
公开(公告)日：2021-11-16
申请号：US16405270
申请日：2019-05-07
发明人： Bang An , HongLei Guo , Shiwan Zhao , Zhong Su
IPC分类号： G06F40/56 , G06F40/30 , G06F40/289 , G06F40/58
摘要： Embodiments of the present disclosure relate to generation of sentence representation. In an embodiment, a method is disclosed. According to the method, a sentence graph is generated from a sentence containing words, the sentence graph comprising nodes representing the words and edges connecting the nodes to indicate relationships between the words. Word representations for the plurality of words are determined based on the sentence graph by applying a graph convolution operation on respective sets of neighbor nodes for respective ones of the nodes, a set of neighbor nodes for a node having edges connected with the node. A sentence representation for the sentence is determined based on the word representations for use in a natural language processing task related to the sentence. In other embodiments, a system and a computer program product are disclosed.
-
公开(公告)号：US11010559B2
公开(公告)日：2021-05-18
申请号：US16117431
申请日：2018-08-30
发明人： Shiwan Zhao , Meng Ting Hu , Li Zhang , Zhi Hu Wang , Zhong Su
摘要： A computer-implemented method is presented for implementing multi-aspect sentiment analysis by collaborative attention allocation. The method includes extracting a sequence of word vectors from a sentence received from a data stream, feeding the sequence of word vectors to long short-term memory (LSTM) neural networks to generate a sequence of hidden states corresponding to the sequence of word vectors, generating a plurality of aspect embedding vectors for each aspect, employing an attention mechanism to determine attention weight vectors concurrently for all aspects, and outputting predicted sentiments for each aspect of the sentence to a user interface of a computing device.
-
公开(公告)号：US20210118424A1
公开(公告)日：2021-04-22
申请号：US17133902
申请日：2020-12-24
发明人： Yue Chen , Lin Luo , Qin Shi , Zhong Su , Changhua Sun , Enliang Xu , Shiwan Zhao
摘要： Techniques for generating a personality trait model are described. According to an example, a system is provided that can generate text data and linguistic data, and apply psycholinguistic data to the text data and the linguistic data, resulting in updated text data and updated linguistic data. The system is further operable to combine the updated text data with the updated linguistic data to generate a personality trait model. In various embodiments, the personality trait model can be trained and updated as additional data is received from various inputs.
-
公开(公告)号：US20210117626A1
公开(公告)日：2021-04-22
申请号：US17133965
申请日：2020-12-24
发明人： Ke Ke Cai , Jing Ding , Zhong Su , Chang Hua Sun , Li Zhang , Shi Wan Zhao
摘要： Techniques are provided for training, by a system operatively coupled to a processor, an attention weighted recurrent neural network encoder-decoder (AWRNNED) using an iterative process based on one or more paragraphs of agent sentences from respective transcripts of one or more conversations between one or more agents and one or more customers, and based on one or more customer response sentences from the respective transcripts, and generating, by the system, one or more groups respectively comprising one or more agent sentences and one or more customer response sentences selected based on attention weights of the AWRNNED.
-
公开(公告)号：US10832458B2
公开(公告)日：2020-11-10
申请号：US16270757
申请日：2019-02-08
发明人： Keke Cai , Dongxu Duan , Zhong Su , Li Zhang , Xiaolu Zhang , Shiwan Zhao
摘要： A method, system, and computer program product, include receiving a first input at a first element among a plurality of elements associated with at least one electronic document, determining a second element associated with the first element from the plurality of elements based on predetermined relations of the plurality of elements, and causing a view to be displayed together with an electronic document including the first element, the view at least including the second element.
-
公开(公告)号：US10832000B2
公开(公告)日：2020-11-10
申请号：US15350355
申请日：2016-11-14
发明人： Dongxu Duan , HongLei Guo , Zhili Guo , Zhong Su , Guoyu Tang , Shiwan Zhao
IPC分类号： G06F40/30 , G06F40/205
摘要： Techniques for determining a similarity between text segments within a document comprising textual references are described. According to an example, a system comprises a memory that stores computer executable components; and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise: an identification component that identifies a reference associated with a set of text and an extraction component that extracts the reference from the set of text. The computer executable components can also comprise an embedding component that replaces the reference with a corresponding vector.
-
公开(公告)号：US10824812B2
公开(公告)日：2020-11-03
申请号：US15175808
申请日：2016-06-07
发明人： Keke Cai , HongLei Guo , Jian Min Jiang , Zhong Su , Changhua Sun , Guoyu Tang
摘要： The methods, systems, and computer program products described herein provide ways to generate an informative training corpus of samples for use in machine training a high-quality sentiment analysis computer model. In some aspects, a method is disclosed including receiving a plurality of training samples, extracting semantic and sentiment elements of one or more of the training samples, generalizing the semantic and sentiment elements of the one or more of the training samples, generating an informative ranking score for one or more of the training samples based on the generalized semantic and sentiment elements, selecting informative training samples from the plurality of training samples based at least in part on the generated informative ranking scores, and adding the selected informative training samples to an informative training corpus.
-
公开(公告)号：US10769213B2
公开(公告)日：2020-09-08
申请号：US15332842
申请日：2016-10-24
发明人： Keke Cai , HongLei Guo , Zhili Guo , Feng Jin , Zhong Su
摘要： Techniques for detection of document similarity are provided. The computer-implemented method can comprise identifying, by an electronic device operatively coupled to a processing unit, a first pragmatic association of a first segment in a first document portion, the first pragmatic association indicating meaning of the first segment specific to a context of the first segment in the first document portion. The computer-implemented method can also comprise generating a first intermediate document portion from the first document portion by using the first pragmatic association to replace the first segment. The computer-implemented method can further comprise determining a similarity degree between the first document portion and a second document portion by comparing the first intermediate document portion with the second document portion.
-
-
-
-
-
-
-
-
-
搜索结果
156 条记录 (耗时 0.03 秒)
