-
公开(公告)号：US11663402B2
公开(公告)日：2023-05-30
申请号：US16934220
申请日：2020-07-21
Applicant: International Business Machines Corporation
Inventor： Chao-Min Chang , Kuei-Ching Lee , Ci-Hao Wu , Chia-Heng Lin
IPC: G06F40/242 , G06F40/295 , G06F40/58
CPC classification number: G06F40/242 , G06F40/295 , G06F40/58
Abstract: An approach for a fast and accurate word embedding model, “desc2vec,” for out-of-dictionary (OOD) words with a model learning from the dictionary descriptions of the word is disclosed. The approach includes determining that a target text element is not in a set of reference text elements, information describing the target text element is obtained. The information comprises a set of descriptive text elements. A set of vectorized representations for the set of descriptive text elements is determined. A target vectorized representation for the target text element is determined based on the set of vectorized representations using a machine learning model. The machine learning model is trained to represent a predetermined association between the set of vectorized representations for the set of descriptive text elements describing the target text element and the target vectorized representation.
-
公开(公告)号：US11768903B2
公开(公告)日：2023-09-26
申请号：US16906077
申请日：2020-06-19
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Chao-Min Chang , Ying-Chen Yu , June-Ray Lin , Kuei-Ching Lee , Curtis C H Wei
IPC: G06F16/95 , G06F16/955 , G06N20/00 , G06N5/04 , G06F40/30 , G06F16/951 , G06F40/169 , G06F40/295 , G06F40/205
CPC classification number: G06F16/955 , G06F16/951 , G06F40/30 , G06N5/04 , G06N20/00 , G06F40/169 , G06F40/205 , G06F40/295
Abstract: A computer-implemented method for automatically adjusting a Uniform Resource Locator (URL) seed list. The method includes crawling for documents based on a seed URL list. The method generates relations data from the documents using a Natural Language Processing (NLP) model. The method analyzes the relations data using an auto-seed model. The method modifies the seed URL list.
-
公开(公告)号：US11983271B2
公开(公告)日：2024-05-14
申请号：US16952494
申请日：2020-11-19
Applicant: International Business Machines Corporation
Inventor： Bruno dos Santos Silva , Cheng-Ta Lee , Ron Williams , Bo-Yu Kuo , Chao-Min Chang , Sridhar Muppidi
CPC classification number: G06F21/566 , G06F21/554 , G06N5/04 , G06N20/00 , G06F2221/034
Abstract: A processor may generate an enforcement point. The enforcement point may include one or more adversarial detection models. The processor may receive user input data. The processor may analyze, at the enforcement point, the user input data. The processor may determine, from the analyzing, whether there is an adversarial attack in the user input data. The processor may generate an alert based on the determining.
-
公开(公告)号：US20220027557A1
公开(公告)日：2022-01-27
申请号：US16934220
申请日：2020-07-21
Applicant: international Business Machines Corporation
Inventor： Chao-Min Chang , Kuei-Ching Lee , Ci-Hao Wu , Chia-Heng Lin
IPC: G06F40/242 , G06N20/00 , G06F40/58 , G06F40/295 , G06K9/62
Abstract: An approach for a fast and accurate word embedding model, “desc2vec,” for out-of-dictionary (OOD) words with a model learning from the dictionary descriptions of the word is disclosed. The approach includes determining that a target text element is not in a set of reference text elements, information describing the target text element is obtained. The information comprises a set of descriptive text elements. A set of vectorized representations for the set of descriptive text elements is determined. A target vectorized representation for the target text element is determined based on the set of vectorized representations using a machine learning model. The machine learning model is trained to represent a predetermined association between the set of vectorized representations for the set of descriptive text elements describing the target text element and the target vectorized representation.
-
-
-
Search Results
4
records
(took 0.013 seconds)
