Chen Han Lin

US Patent:

20210133284, May 6, 2021

Filed:

Oct 31, 2019

Appl. No.:

16/671047

Inventors:

- Armonk NY, US
Chen Lin - Elmsford NY, US
Jin Xiao - White Plains NY, US
Maja Vukovic - New York NY, US

International Classification:

G06F 17/27
G06K 9/00
G06K 9/62
G06N 20/00

Abstract:

One embodiment of the invention provides a method for entity extraction, comprising determining a set of part-of-speech (POS) tags based on one or more documents, determining a concept in the one or more documents based on the set of POS tags, and extracting one or more phrases from the one or more documents based on the concept. The method further comprises generating a first set of rules corresponding to the concept based on the one or more phrases, generating a second set of rules specific to a domain based on the first set of rules, and learning, via an adapter grammar, a structure of one or more named entities in the one or more documents based on the second set of rules.

US Patent:

20200257733, Aug 13, 2020

Filed:

Feb 13, 2019

Appl. No.:

16/274867

Inventors:

- Armonk NY, US
Jie Ma - Nanjing, CN
Ya Bin Dang - Beijing, CN
Jinho Hwang - Ossining NY, US
Chen Lin - Elmsford NY, US
John Rofrano - Mahopac NY, US
Anup Kalia - Elmsford NY, US
Maja Vukovic - New York NY, US

International Classification:

G06F 16/9032
G10L 15/22
G06F 16/9035
G06F 16/9038
G10L 25/30
G10L 25/54

Abstract:

Systems and methods for prioritizing interview questions, including predicting answers to questions in a candidate question set using a neural network model, and generating a ranking for each of the questions in the candidate question set by determining answer confidence, completeness, and ambiguity for each of the answers, and incorporating user preferences using a personalized preference matrix. A top ranked question is automatically selected and presented to the user, and the personalized preference matrix is iteratively adjusted for subsequent ranking of questions based on an answer to the top ranked question by the user to reduce computational resources expended

US Patent:

20190188276, Jun 20, 2019

Filed:

Dec 20, 2017

Appl. No.:

15/848563

Inventors:

- Armonk NY, US
Anup Kalia - Elmsford NY, US
Chen Lin - Raleigh NC, US
Maja Vukovic - New York NY, US
Jin Xiao - Ossining NY, US

International Classification:

G06F 17/30
G06F 9/50
G06F 17/27
G06K 9/62

Abstract:

Techniques for generating domain and client-specific application program interface recommendations are provided. In one example, a computer-implemented method comprises determining a semantic similarity between a first client application program interface and a second client application program interface based on a modified client application program interface being generated by removing text data associated with a first description of the first client application program interface. The computer-implemented method can further comprise matching the first description to a second description of the second client application program interface based on the semantic similarity, resulting in on or more matched client application program interfaces. Additionally, the computer-implemented method can further comprise associating the first client application program interface with a community based on the one or more matched client application program interfaces.

US Patent:

20190188319, Jun 20, 2019

Filed:

Dec 20, 2017

Appl. No.:

15/848589

Inventors:

- Armonk NY, US
Anup Kalia - Elmsford NY, US
Chen Lin - Raleigh NC, US
Maja Vukovic - New York NY, US
Jin Xiao - Ossining NY, US

International Classification:

G06F 17/30
G06F 17/27
G06K 9/62

Abstract:

Techniques for generating domain and client-specific application program interface recommendations are provided. In one example, a computer-implemented method comprises modifying, by a device operatively coupled to a processor, a description of a client application program interface by removing text data associated with the description of the client application program interface, resulting in a modified description of the client application program interface. The computer-implemented method can further comprise analyzing, by the device, a performance associated with the client application program interface to generate an ontology based on a semantic similarity between the modified description of the client application program interface and one or more previous descriptions of one or more previous client application program interfaces.