-
公开(公告)号：US20210103706A1
公开(公告)日：2021-04-08
申请号：US17060850
申请日：2020-10-01
发明人： Wenchao Yu , Bo Zong , Wei Cheng , Haifeng Chen , Xiusi Chen
摘要： Methods and systems for performing a knowledge graph task include aligning multiple knowledge graphs and performing a knowledge graph task using the aligned multiple knowledge graphs. Aligning the multiple knowledge graphs includes updating entity representations based on representations of neighboring entities within each knowledge graph, updating entity representations based on representations of entities from different knowledge graphs, and learning machine learning model parameters to align the multiple knowledge graphs, based on the updated entity representations.
-
公开(公告)号：US20210081612A1
公开(公告)日：2021-03-18
申请号：US16970315
申请日：2019-02-15
发明人： Itsumi SAITO , Kyosuke NISHIDA , Junji TOMITA , Hisako ASANO
IPC分类号： G06F40/289 , G06N3/02 , G06K9/62 , G06F40/169 , G06F40/44
摘要： A relationship between phrases can be accurately estimated without incurring the cost of generating learning data. A learning data generation unit 62 extracts a pair of phrases having a dependency relationship with a segment containing a predetermined connection expression representing a relationship between phrases based on a dependency analysis result for input text, and generates a triple consisting of the extracted pair of phrases, and the connection expression or a relation label indicating a relationship represented by the connection expression. A learning unit 63 learns the relationship estimation model for estimating a relationship between phrases based on the triple generated by the learning data generation unit.
-
公开(公告)号：US20210049329A1
公开(公告)日：2021-02-18
申请号：US17071608
申请日：2020-10-15
发明人： Boris Galitsky
IPC分类号： G06F40/35 , G06F16/31 , G06F16/332 , G06F40/44 , G06F40/51 , G06F40/55 , G06F40/211 , G06K9/62 , G06N3/08
摘要： Systems, devices, and methods of the present invention calculate a rhetorical relationship between one or more sentences. In an example, a computer-implemented method accesses a sentence comprising a plurality of fragments. At least one fragment includes a verb and a words. Each word includes a role of the words within the fragment. Each fragment is an elementary discourse unit. The method generates a discourse tree that represents rhetorical relationships between the sentence fragments. The discourse tree includes nodes including nonterminal and terminal nodes, each nonterminal node representing a rhetorical relationship between two of the sentence fragments, and each terminal node of the nodes of the discourse tree is associated with one of the sentence fragments. The method matches each fragment that has a verb to a verb signature, thereby creating communicative discourse tree.
-
公开(公告)号：US20210042475A1
公开(公告)日：2021-02-11
申请号：US16939692
申请日：2020-07-27
申请人： Yappn Canada Inc.
发明人： Renxian Zhang , Jinnan Lu , Zhanxuan Ding , Jie Ma , Syed Salman Ali , Jason Cox , Xun Li
摘要： Provided are computer implemented systems and methods for providing improved language translation, including translation of input text to an output translated text element. This may include providing for rule-based language translation. This may further include a plurality of machine translation models adapted to different translation domains. A machine translation selector is described that selects an in-domain machine translator from the plurality of machine translation models based on an input text element. The selected in-domain machine translator may generate a first translated text element from the input text element. A post-editor module may generate a second translated text element by predicting a post-edit to the first translated text element. The first translated text element and the second translated text element are evaluated by a quality evaluation model that determines a first metric associated with the first translated text element and a second metric associated with the second text element.
-
35.发明申请公开(公告)号：US20210027009A1
公开(公告)日：2021-01-28
申请号：US16981064
申请日：2019-03-11
发明人： Dai IKARASHI
IPC分类号： G06F40/126 , G06F40/131 , G06F40/44
摘要： A calculation process is efficiently performed to a text file in which one or more records are included, each of the records includes one or more cells having an arbitrary length, and each of the cells includes arbitrary pieces of characters. A parameter setting apparatus sets a maximum value Scsv and a minimum value scsv of a size of character strings for one record by using attribute information as an input, a maximum value Senc of a total size of encode information, a maximum value Sss of a total size of a calculation value obtained by performing specific calculation to the encode information, and a total size Sref of reference information, obtains a function value of C/(Scsv+Senc+Sref) as the number of records which is a process unit of encoding and calculation, and obtains a function value of f0/I·r·Scsv as the number of parallels in the calculation process. Here, C is a cache memory size, M is a main memory size, and f0 is a function value of scsv·M/(scsv+Senc+max(Sref,Sss)).
-
公开(公告)号：US10884771B2
公开(公告)日：2021-01-05
申请号：US16237262
申请日：2018-12-31
发明人： Qiugen Xiao
IPC分类号： G06F17/27 , G06F9/451 , G06F40/44 , G06F40/58 , G06F40/103 , G06F40/129 , G06F40/263 , G06F40/279
摘要： The present disclosure provides a method and a device for displaying multi-language typesetting, a browser, a terminal and a computer readable storage medium. The method includes: obtaining a text to be typeset; identifying embedded language content in a principal language text of the text to be typeset, wherein the embedded language content comprises at least one non-principal language content embedded in the principal language text; determining replacement content of the embedded language content, wherein the replacement content comprises a principal language text corresponding to the embedded language content or an abbreviation of a non-principal language text in the embedded language content; and replacing the embedded language content with the replacement content.
-
公开(公告)号：US10853581B2
公开(公告)日：2020-12-01
申请号：US15975685
申请日：2018-05-09
发明人： Boris Galitsky
IPC分类号： G06F40/211 , G06F40/30 , G06F40/35 , G06F16/31 , G06F16/332 , G06F40/44 , G06F40/51 , G06F40/55 , G06K9/62 , G06N3/08
摘要： Systems, devices, and methods of the present invention calculate a rhetorical relationship between one or more sentences. In an example, a computer-implemented method accesses a sentence comprising a plurality of fragments. At least one fragment includes a verb and a words. Each word includes a role of the words within the fragment. Each fragment is an elementary discourse unit. The method generates a discourse tree that represents rhetorical relationships between the sentence fragments. The discourse tree includes nodes including nonterminal and terminal nodes, each nonterminal node representing a rhetorical relationship between two of the sentence fragments, and each terminal node of the nodes of the discourse tree is associated with one of the sentence fragments. The method matches each fragment that has a verb to a verb signature, thereby creating communicative discourse tree.
-
公开(公告)号：US10810379B2
公开(公告)日：2020-10-20
申请号：US16286444
申请日：2019-02-26
发明人： Xiaodong Zeng , Weihua Luo , Feng Lin
IPC分类号： G06F17/28 , G06F40/44 , G06F40/30 , G06F40/55 , G06F40/205
摘要： A statistics-based machine translation method is disclosed. The method generates probabilities of translation from a sentence to be translated to candidate translated texts based on features of the candidate translated texts that affect the probabilities of translation and a pre-generated translation probability prediction model. The features that affect probabilities of translation include at least degrees of semantic similarity between the sentence to be translated and the candidate translated texts. A preset number of candidate translated texts with highly ranked probabilities of translation are selected to serve as translated texts of the sentence to be translated. The method is able to go deep into a semantic level of a natural language when a machine translation model is constructed to avoid a semantic deviation of a translated text from an original text, thereby achieving the effect of improving the quality of translation.
-
公开(公告)号：US20200234011A1
公开(公告)日：2020-07-23
申请号：US16751167
申请日：2020-01-23
申请人： Google LLC
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating network outputs using insertion operations.
-
公开(公告)号：US10691685B2
公开(公告)日：2020-06-23
申请号：US15721705
申请日：2017-09-29
申请人： Apple Inc.
发明人： Vishal Verma , Gang Xiang , Vishnu Konda , Chetan V. Kale
IPC分类号： G06F16/2452 , G06N5/02 , G06F16/248 , G06F16/2458 , G06F16/332 , G06F16/33 , G06N3/04 , G06F40/30 , G06F40/44 , G06F40/211 , G06F40/295
摘要： The subject technology provides for converting natural language input to structured queries. The subject technology receives a user input query in a natural language format. The subject technology determines scores for candidate entities derived from the user input query. The subject technology selects an entity with a highest score among the candidate entities, and converts, using a context-free grammar, the user input query to a structured query based at least in part on the selected entity. The subject technology classifies the structured query to an expected answer type, the expected answer type corresponding to a type of an expected answer of the structured query. The subject technology queries a database based on the expected answer type and the structured query, the database including information corresponding to a knowledge graph. The subject technology provides, for display, an answer to the user input query based on a result of querying the database.
-
-
-
-
-
-
-
-
-
搜索结果
254 条记录 (耗时 0.018 秒)
