公开(公告)号：US20250117581A1

公开(公告)日：2025-04-10

申请号：US18729950

申请日：2022-01-25

Applicant: NEC Corporation

Inventor： Masafumi OYAMADA ,  Taro YANO ,  Kunihiro TAKEOKA ,  Kosuke AKIMOTO

IPC: G06F40/279 ,  G06F40/40

Abstract: In order to classify, stably with high accuracy, a document to be classified, a document classification apparatus (1) includes: a strategy selection section (11) that selects at least one generation strategy from among a plurality of generation strategies for generating a hypothetical sentence related to a candidate classification as which a document is to be classified; a hypothetical sentence generation section (12) that generates, in accordance with the at least one generation strategy selected by the strategy selection section (11), the hypothetical sentence, which is a sentence related to the candidate classification; and a classification section (13) that determines, on the basis of entailment between the document and the hypothetical sentence, a classification as which the document is to be classified.

公开(公告)号：US20250124313A1

公开(公告)日：2025-04-17

申请号：US18703421

申请日：2021-11-11

Applicant: NEC Corporation

Inventor： Kosuke AKIMOTO ,  Kunihiro TAKEOKA ,  Masafumi OYAMADA

IPC: G06N5/048 ,  G06F40/279

Abstract: To determine, with high accuracy, a label to be given to an object even in a case where only a single prediction model exists, an information processing apparatus (1) includes: an acquisition unit (11) that acquires a set of objects; an evaluation unit (12) that evaluates a degree of similarity between objects included in the set of objects and identifies one or a plurality of similar objects which are similar to a prediction target object; and a prediction unit (13) that determines a label to be given to the prediction target object with reference to a similar label(s), the similar label(s) being a label(s) which is/are given to each of the one or a plurality of similar objects and which has/have been predicted by a prediction model.

公开(公告)号：US20240185022A1

公开(公告)日：2024-06-06

申请号：US18519286

申请日：2023-11-27

Applicant: NEC Corporation

Inventor： Kosuke AKIMOTO ,  Kunihiro Takeoka

IPC: G06N3/006 ,  G06N7/01 ,  G06N20/00

CPC classification number: G06N3/006 ,  G06N7/01 ,  G06N20/00

Abstract: At least one processor included in a question generation apparatus carries out: a an acquiring process of acquiring a first question to which there are a plurality of answers; a question generating process of generating, for each of the plurality of answers, a second question an answer to which is a character string indicating that answer; an ambiguity verifying process of verifying how many answers there are; and an outputting process of outputting the second question which has fewer answers than the first question, in accordance with a result of verification.

公开(公告)号：US20220222442A1

公开(公告)日：2022-07-14

申请号：US17614646

申请日：2019-05-31

Applicant: NEC Corporation

Inventor： Kosuke AKIMOTO ,  Takuya HIRAOKA ,  Kunihiko SADAMASA

IPC: G06F40/295 ,  G06N3/04

Abstract: A parameter learning apparatus 100 extracts one entity in a document and a related text representation as a one-term document fact, outputs a one-term partial predicate fact including only the one entity using a predicate fact that includes entities and a predicate, calculates a first one-term score indicating the degree of establishment of the one-term document fact using a one-term partial predicate feature vector, a one-term text representation feature vector, and a one-term entity feature vector that are calculated from parameters, calculates a second one-term score with respect to a combination of one entity and a predicate or a text representation that is not extracted as the one-term partial predicate fact, updates the parameters such that the first one-term score is higher than the second one-term score, and calculates a score indicating the degree of establishment of the predicate fact and a score indicating the degree of establishment of a combination of entities and a predicate that is not obtained as the predicate fact using these scores.

公开(公告)号：US20230143808A1

公开(公告)日：2023-05-11

申请号：US17914546

申请日：2020-03-27

Applicant: NEC Corporation

Inventor： Kosuke AKIMOTO ,  Seng Pei LIEW ,  Ryo MIZUSHIMA ,  Kong Aik LEE

IPC: G06F21/32

CPC classification number: G06F21/32

Abstract: A feature calculation means calculates N features for first data and N features for second data by using N feature functions for obtaining a feature for data on the basis of the data. A similarity degree calculation means calculates a similarity degree between the first data and the second data on the basis of the N features for the first data and the N features for the second data. Values of N features obtained when the same data is substituted into the N feature functions are different from each other.

公开(公告)号：US20220245183A1

公开(公告)日：2022-08-04

申请号：US17613549

申请日：2019-05-31

Applicant: NEC Corporation

Inventor： Kosuke AKIMOTO ,  Takuya HIRAOKA ,  Kunihiko SADAMASA

IPC: G06F16/33 ,  G06N3/04

Abstract: An entity combination and a text representation are obtained as a first fact, and the entity combination and a related predicate are obtained as a second fact. Word distributed representations are input to a neural network, real vectors at appearance positions of entities are specified and used as distributed representations. A first score indicating a degree of establishment of the first fact is calculated based on the distributed representations and on entity distributed representations. A second score indicating a degree of establishment is calculated with respect to an entity combination and a text representation that are not the first fact. A third score indicating a degree of establishment of the second fact is calculated based on predicate distributed representations and on entity distributed representations. A fourth score indicating a degree of establishment is calculated also with respect to an entity combination and a predicate that are not the second fact. The entity distributed representations, the predicate distributed representations, or weight parameters are updated by a gradient method, so that the first score becomes higher than one of the second score and the fourth score, and the third score becomes higher than one of the second score and the fourth score.