Lin Pan from Braintree, MA, age 49

Resumes

Cognitive Software Engineer

view source

Location:

Somerville, MA

Industry:

Computer Software

Work:

Ibm
Cognitive Software Engineer
Sap Mar 2012 - Jun 2013
Computational Linguist
Brandeis University Feb 1, 2010 - Feb 1, 2011
Research Assistant

Education:

Brandeis University 2009 - 2011
Masters, Master of Arts, Linguistics Beijing Language and Culture University 2004 - 2008
Bachelors, Bachelor of Arts, Korean Language, Linguistics Brandeis University
Masters

Skills:

Natural Language Processing
Sentiment Analysis
Machine Learning
Python
Computational Linguistics
Computer Science
Data Mining
Java
Text Analytics
Information Retrieval
Semantics
Text Mining
Artificial Intelligence
Text Classification
Spss
Lua
Torch
Formal Semantics

Languages:

Mandarin
English
Korean

Tax Associate

view source

Location:

Buffalo, NY

Industry:

Accounting

Work:

Pwc
Tax Associate
Center For Academic Development Services Lab University at Buffalo
Tutor
Ss&C Technologies Jun 2011 - Aug 2011
Accounting Intern

Education:

University at Buffalo May 2013
Master of Science, Masters University at Buffalo School of Management, the State University of New York 2012 - 2013
University at Buffalo Feb 2012
University at Buffalo School of Management, the State University of New York 2008 - 2012
Bachelors, Bachelor of Science, Accounting

Skills:

Mandarin
Bloomberg Terminal
Microsoft Office
Microsoft Dynamics
Total Return

Lin Yu Pan

view source

Lin Pan

view source

Lin Pan

view source

Work:

Brandeis University

Jan 2010 to 2000
Research Assistant

Education:

Brandeis University
Waltham, MA
Jan 2009 to Jan 2011
MA in Computational Linguistics

Skills:

Proficiency in Python, Java, and C

Us Patents

Intent Classification Using Non-Correlated Features
view source
US Patent:

20220405472, Dec 22, 2022
Filed:

Jun 17, 2021
Appl. No.:

17/350116
Inventors:

- Armonk NY, US
Ladislav Kunc - Cambridge MA, US
Haode Qi - Cambridge MA, US
LIN PAN - Acton MA, US
Saloni Potdar - Arlington MA, US
International Classification:

G06F 40/284
G06F 16/33
G06F 16/35
G06N 20/00
G06N 5/04
Abstract:

A system for classifying a language sample intent by receiving a language sample including a set of features, identifying language sample features, determining a tokenization score for the language sample according to the language sample features, eliminating duplicate features according to the tokenization score, determining a term frequency (tf) according to the identified features and the tokenization score, determining an inverse document frequency (idf) according to the identified features and the tokenization score, and generating a term frequency-inverse document frequency (tf-idf) matrix for the identified features.

Conversational Ai With Multi-Lingual Human Chatlogs
view source
US Patent:

20220391600, Dec 8, 2022
Filed:

Jun 7, 2021
Appl. No.:

17/303728
Inventors:

- ARMONK NY, US
LIN PAN - Acton MA, US
Abhishek Shah - JERSEY CITY NJ, US
Ladislav Kunc - Cambridge MA, US
Saloni Potdar - Arlington MA, US
International Classification:

G06F 40/58
G06F 40/35
G06F 40/44
G06N 20/00
G06K 9/62
H04L 12/58
Abstract:

A method, computer system, and computer program product for multi-lingual chatlog training are provided. The embodiment may include receiving, by a processor, a plurality of data related to conversational data in multiple languages. The embodiment may also include assigning an intent label to each conversational data. The embodiment may further include assigning a language label to each conversational data. The embodiment may also include paring the plurality of the data related to the conversational data according to the intent label and the language label. The embodiment may further include training a machine learning model using a multi-lingual and multi-intent conversational data pairing. The embodiment may also include training the machine learning model using a single language and multi-intent conversational data paring.