专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20220343084A1 TRANSLATION APPARATUS, TRANSLATION METHOD AND PROGRAM 有权
公开(公告)号：US20220343084A1
公开(公告)日：2022-10-27
申请号：US17639459
申请日：2020-08-25
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Masaaki NAGATA , Yuto TAKEBAYASHI , Chenhui CHU , Yuki ARASE
IPC分类号： G06F40/49 , G06F40/242 , G06F40/284
摘要： A translation apparatus includes: a preprocessing unit that takes an input sentence in a source language and outputs a token string in which the input sentence has been segmented in tokens, the tokens being a predetermined unit of processing; an output sequence prediction unit that inputs the token string output by the preprocessing unit to a trained translation model and predicts a word translation probability of a translation candidate for each token of the token string from the trained translation model; a word set prediction unit that checks each token of the token string output by the preprocessing unit against entry words of a bilingual dictionary, and upon detecting an entry word that agrees with the token in the bilingual dictionary, generates a target-language word set from a set of tokens constituting a translation phrase corresponding to the detected entry word; and an output sequence determination unit that computes a reward which is based on whether a translation candidate for each token of the input sentence is included in the target-language word set or not and determines a translated sentence of the input sentence based on a word translation score computed by adding the reward to the word translation probability of the translation candidate. Units of tokens constituting the translation phrase in the bilingual dictionary are subwords.

2. 发明申请

US20220215182A1 INFORMATION PROCESSING APPARATUS, INFORMATION LEARNING APPARATUS, INFORMATION PROCESSING METHOD, INFORMATION LEARNING METHOD AND PROGRAM 有权
公开(公告)号：US20220215182A1
公开(公告)日：2022-07-07
申请号：US17610589
申请日：2019-05-21
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Makoto MORISHITA , Jun SUZUKI , Sho TAKASE , Hidetaka KAMIGAITO , Masaaki NAGATA
IPC分类号： G06F40/44 , G06N3/04
摘要： An information learning apparatus includes a memory and a processor configured to perform generating, for each of processing units constituting an input sequence included in training data, a third embedded vector based on a first embedded vector for the processing unit and a second embedded vector corresponding to an unknown word; executing a process based on a learning target parameter, with the third embedded vector generated for each of the processing units as an input; and learning, for a processing result by the executing, the parameter based on an error of an output corresponding to the input sequence in the training data.

3. 发明申请

US20220229982A1 INFORMATION PROCESSING APPARATUS, INFORMATION LEARNING APPARATUS, INFORMATION PROCESSING METHOD, INFORMATION LEARNING METHOD AND PROGRAM 有权
公开(公告)号：US20220229982A1
公开(公告)日：2022-07-21
申请号：US17611905
申请日：2019-05-21
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Makoto MORISHITA , Jun SUZUKI , Sho TAKASE , Hidetaka KAMIGAITO , Masaaki NAGATA
IPC分类号： G06F40/268 , G06N3/08
摘要： An information processing apparatus includes a memory and a processor configured to perform generating subword units of a plurality of layers for each of processing units constituting an input sequence and generating an embedded vector based on the subword units of the plurality of layers for each of the processing units; and executing a process based on a learned parameter, with the embedded vector generated for each of the processing units as an input.

4. 发明申请

US20220189468A1 ABSTRACT GENERATION DEVICE, METHOD, PROGRAM, AND RECORDING MEDIUM 有权
公开(公告)号：US20220189468A1
公开(公告)日：2022-06-16
申请号：US17425696
申请日：2020-01-16
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Tsutomu HIRAO , Atsunori OGAWA , Tomohiro NAKATANI , Masaaki NAGATA
IPC分类号： G10L15/193 , G10L15/22 , G10L15/08
摘要： A speech recognition unit (12) converts an input utterance sequence into a confusion network sequence constituted by a k-best of candidate words of speech recognition results; a lattice generating unit (14) generates a lattice sequence having the candidate words as internal nodes and a combination of k words among the candidate words for an identical speech as an external node, in which edges are extended between internal nodes other than internal nodes included in an identical external node, from the confusion network sequence; an integer programming problem generating unit (16) generates an integer programming problem for selecting a path that maximizes an objective function including at least a coverage score of an important word, of paths following the internal nodes with the edges extended, in the lattice sequence; and the summary generating unit generates a high-quality summary having less speech recognition errors and low redundancy using candidate words indicated by the internal nodes included in the path selected by solving the integer programming problem, under a constraint on the length of a summary to be generated.

5. 发明申请

US20220366155A1 INFORMATION LEARNING APPARATUS, INFORMATION PROCESSING APPARATUS, INFORMATION LEARNING METHOD, INFORMATION PROCESSING METHOD AND PROGRAM 有权
公开(公告)号：US20220366155A1
公开(公告)日：2022-11-17
申请号：US17618372
申请日：2019-06-14
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Makoto MORISHITA , Jun SUZUKI , Masaaki NAGATA
IPC分类号： G06F40/58 , G06N3/08
摘要： An information learning apparatus includes a memory and a processor configured to perform encoding first data in training data in which the first data related to a first series and second data which is correct data for the first data in a second series are associated with each other; decoding data generated in the encoding to generate third data related to the second series; fourth data related to the first series for data generated in the decoding; and learning, based on an error between the second data and the third data and an error between the first data and the fourth data, parameters used by the encoding, the decoding, and the generating, wherein the generating and the encoding share parameters.

6. 发明申请

US20220138434A1 GENERATION APPARATUS, GENERATION METHOD AND PROGRAM 有权
公开(公告)号：US20220138434A1
公开(公告)日：2022-05-05
申请号：US17435002
申请日：2020-02-21
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Masaaki NISHINO , Tsutomu HIRAO , Masaaki NAGATA
IPC分类号： G06F40/40 , G06F40/205 , G06F17/16
摘要： Included are input means for inputting first data that is data relating to a plurality of letters included in a text string that is a generation target, and generating means for generating second data that is data relating to the text string that satisfies predetermined constraint conditions including at least a condition relating to plausibility of the sequence of letters, on the basis of the first data.

7. 发明申请

US20220075844A1 FAST SPARSE OPTIMIZATION DEVICE, FAST SPARSE OPTIMIZATION METHOD, AND PROGRAM 有权
公开(公告)号：US20220075844A1
公开(公告)日：2022-03-10
申请号：US17417352
申请日：2019-12-17
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Shinsaku SAKAUE , Masaaki NAGATA
IPC分类号： G06F17/16
摘要： An object is to make it possible to find a high-quality solution at a high speed even for a nonconvex sparse optimization problem of bad conditions. A computation unit 130 computes, with respect to each element that is not included in a set of nonzero elements that is previously obtained or an initial value of the set of nonzero elements, an optimum value of an objective function in a case in which elements that are allowed to be nonzero elements are only elements included in a set that is obtained by adding the element not included in the set of nonzero elements to the set of nonzero elements. A main processing unit 120 selects added elements in the order of optimum values of the objective function and adds the selected elements to the set of nonzero elements, the number of selected elements being an addition upper limit number determined in advance for each number of times of repetition such that a sum total of addition upper limit numbers is a predetermined number, the elements being selected such that an element with which a preferable optimum value can be obtained is preferentially selected. A determination unit 140 causes the computation unit 130 to repeatedly perform computation and causes the main processing unit 120 to repeatedly perform selection and addition. An output unit 150 outputs a value of the variable vector that optimizes the value of the objective function when only the set of nonzero elements is allowed to be nonzero elements.

8. 发明申请

US20210342529A1 WORD CODING DEVICE, ANALYSIS DEVICE, LANGUAGE MODEL LEARNING DEVICE, METHOD, AND PROGRAM 有权
公开(公告)号：US20210342529A1
公开(公告)日：2021-11-04
申请号：US17269665
申请日：2019-08-22
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Sho TAKASE , Masaaki NAGATA
IPC分类号： G06F40/20 , G06N3/04 , G06N3/08
摘要： To generate a vector representing a word in consideration of the importance of the character string of the word. A character N-gram vector acquisition unit acquires a vector representing each of character N-grams included in a word. A weight calculation unit 40 calculates a weight for a vector representing each of the character N-grams on the basis of the vector representing each of the character N-grams included in the word, and a character N-gram vector combining unit 42 generates a composite vector obtained by combining the vector representing each of the character N-grams on the basis of the vector representing each of the character N-grams included in the word and the weight for the vector representing each of the character N-grams.

9. 发明申请

US20230099518A1 CLASS-LABELED SPAN SEQUENCE IDENTIFYING APPARATUS, CLASS-LABELED SPAN SEQUENCE IDENTIFYING METHOD AND PROGRAM 有权
公开(公告)号：US20230099518A1
公开(公告)日：2023-03-30
申请号：US17908487
申请日：2020-03-05
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Tsutomu HIRAO , Masaaki NAGATA
IPC分类号： G06F16/35 , G06F40/40 , G06F40/205
摘要： A class-labeled span sequence identification apparatus includes a span generation unit that generates all spans generable from a unit sequence input, a calculation unit that calculates a probability that each of the spans belongs to an individual class of a plurality of predefined classes, and an identification unit that identifies, from among span sequences generable in accordance with the spans, a class-labeled span sequence having a maximum product of a plurality of the probabilities or a maximum sum of scores according to the plurality of the probabilities, and thereby, improves accuracy of a class segmentation position in the unit sequence.

10. 发明申请

US20220277144A1 WORD EMBEDDING VECTOR INTEGRATION DEVICE, WORD EMBEDDING VECTOR INTEGRATION METHOD, AND WORD EMBEDDING VECTOR INTEGRATION PROGRAM 有权
公开(公告)号：US20220277144A1
公开(公告)日：2022-09-01
申请号：US17620680
申请日：2020-06-15
申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION
发明人： Tsutomu HIRAO , Masaaki NAGATA , Katsuhiko HAYASHI
IPC分类号： G06F40/30 , G06F40/279 , G06F40/216
摘要： To make it possible to efficiently learn word embedding vectors of respective words contained in two corpora.
A basis vector correspondence determination unit 22 determines correspondence between basis vectors obtained from word embedding vectors of respective words generated from a corpus A and basis vectors obtained from word embedding vectors of respective words generated from a corpus B. Based on the determined correspondence, a word embedding vector integration unit 24 changes the word embedding vectors of the respective words contained in the corpus B so as to rearrange elements of the word embedding vectors of the respective words contained in the corpus B.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式