Career records & work history
Lawyers & Attorneys
Joseph S Reisinger, 41San Francisco, CA
Joseph Reisinger Phones & Addresses
San Francisco, CA
Austin, TX
Mountain View, CA
198 Cochrans Green Cir, Spring, TX 77381
The Woodlands, TX
St Simons Island, GA
Social networks
Joseph S Reisinger
Linkedin
Work
Company:
Premise data corporation Jan 2012
Position:
Co-founder
Education
Degree:
PhD
School / High School:
The University of Texas at Austin 2005 to 2012
Specialities:
Machine Learning / Natural Language Processing
Skills
Japanese • Machine Learning • Information Extraction • Natural Language Processing • Data Mining • Statistics • Text Mining • Scala • Extreme Environments • Panglossian Thinking
Languages
Japanese • Chinese • French
Interests
Machine Learning, Large-Scale Data Mining, Statistics, Natural Language Processing, Information Extraction, Computer Vision
Industries
Research
Mentions for Joseph S Reisinger
Joseph Reisinger resumes & CV records
Resumes
Premise
Position:
Co-founder at Premise Data Corporation
Location:
San Francisco, California
Industry:
Research
Work:
Premise Data Corporation
since Jan 2012
Co-founder Google Aug 2010 - May 2012
PhD Fellow Metamarkets Oct 2010 - Jan 2012
Chief Scientist Google May 2007 - Oct 2010
Researcher in NLP / Ads Quality IBM May 2003 - Aug 2005
Researcher in Human Language Technologies
Co-founder Google Aug 2010 - May 2012
PhD Fellow Metamarkets Oct 2010 - Jan 2012
Chief Scientist Google May 2007 - Oct 2010
Researcher in NLP / Ads Quality IBM May 2003 - Aug 2005
Researcher in Human Language Technologies
Education:
The University of Texas at Austin 2005 - 2012
PhD, Machine Learning / Natural Language Processing The University of Texas at Austin 2005 - 2007
MS, Computer Science The University of Texas at Austin 2000 - 2004
Double BS, Computer Sciences, Mathematics
PhD, Machine Learning / Natural Language Processing The University of Texas at Austin 2005 - 2007
MS, Computer Science The University of Texas at Austin 2000 - 2004
Double BS, Computer Sciences, Mathematics
Skills:
Japanese, Machine Learning, Information Extraction, Natural Language Processing, Data Mining, Statistics, Text Mining, Scala, Extreme Environments, Panglossian Thinking
Interests:
Machine Learning, Large-Scale Data Mining, Statistics, Natural Language Processing, Information Extraction, Computer Vision
Languages:
Japanese
Chinese
French
Chinese
French
Publications & IP owners
Us Patents
Hierarchical Methods And Apparatus For Extracting User Intent From Spoken Utterances
US Patent:
8560325, Oct 15, 2013
Filed:
Aug 1, 2012
Appl. No.:
13/564596
Inventors:
Dimitri Kanevsky - Ossining NY, US
Joseph Simon Reisinger - Austin TX, US
Roberto Sicconi - Ridgefield CT, US
Mahesh Viswanathan - Yorktown Heights NY, US
Joseph Simon Reisinger - Austin TX, US
Roberto Sicconi - Ridgefield CT, US
Mahesh Viswanathan - Yorktown Heights NY, US
Assignee:
Nuance Communications, Inc. - Burlington MA
International Classification:
G10L 21/00
US Classification:
704275, 704251, 704270
Abstract:
Improved techniques are disclosed for permitting a user to employ more human-based grammar (i. e. , free form or conversational input) while addressing a target system via a voice system. For example, a technique for determining intent associated with a spoken utterance of a user comprises the following steps/operations. Decoded speech uttered by the user is obtained. An intent is then extracted from the decoded speech uttered by the user. The intent is extracted in an iterative manner such that a first class is determined after a first iteration and a sub-class of the first class is determined after a second iteration. The first class and the sub-class of the first class are hierarchically indicative of the intent of the user, e. g. , a target and data that may be associated with the target.
Hierarchical Methods And Apparatus For Extracting User Intent From Spoken Utterances
US Patent:
2007005, Mar 8, 2007
Filed:
Aug 31, 2005
Appl. No.:
11/216483
Inventors:
Dimitri Kanevsky - Ossining NY, US
Joseph Reisinger - Austin TX, US
Robert Sicconi - Ridgefield CT, US
Mahesh Viswanathan - Yorktown Heights NY, US
Joseph Reisinger - Austin TX, US
Robert Sicconi - Ridgefield CT, US
Mahesh Viswanathan - Yorktown Heights NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G10L 21/00
US Classification:
704275000
Abstract:
Improved techniques are disclosed for permitting a user to employ more human-based grammar (i.e., free form or conversational input) while addressing a target system via a voice system. For example, a technique for determining intent associated with a spoken utterance of a user comprises the following steps/operations. Decoded speech uttered by the user is obtained. An intent is then extracted from the decoded speech uttered by the user. The intent is extracted in an iterative manner such that a first class is determined after a first iteration and a sub-class of the first class is determined after a second iteration. The first class and the sub-class of the first class are hierarchically indicative of the intent of the user, e.g., a target and data that may be associated with the target. The multi-stage intent extraction approach may have more than two iterations. By way of example only, the user intent extracting step may further determine a sub-class of the sub-class of the first class after a third iteration, such that the first class, the sub-class of the first class, and the sub-class of the sub-class of the first class are hierarchically indicative of the intent of the user.
Hierarchical Methods And Apparatus For Extracting User Intent From Spoken Utterances
US Patent:
2008022, Sep 11, 2008
Filed:
May 22, 2008
Appl. No.:
12/125441
Inventors:
Dimitri Kanevsky - Ossining NY, US
Joseph Simon Reisinger - Austin TX, US
Robert Sicconi - Ridgefield CT, US
Mahesh Viswanathan - Yorktown Heights NY, US
Joseph Simon Reisinger - Austin TX, US
Robert Sicconi - Ridgefield CT, US
Mahesh Viswanathan - Yorktown Heights NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G10L 21/00
US Classification:
704275, 704E15026
Abstract:
Improved techniques are disclosed for permitting a user to employ more human-based grammar (i.e., free form or conversational input) while addressing a target system via a voice system. For example, a technique for determining intent associated with a spoken utterance of a user comprises the following steps/operations. Decoded speech uttered by the user is obtained. An intent is then extracted from the decoded speech uttered by the user. The intent is extracted in an iterative manner such that a first class is determined after a first iteration and a sub-class of the first class is determined after a second iteration. The first class and the sub-class of the first class are hierarchically indicative of the intent of the user, e.g., a target and data that may be associated with the target. The multi-stage intent extraction approach may have more than two iterations. By way of example only, the user intent extracting step may further determine a sub-class of the sub-class of the first class after a third iteration, such that the first class, the sub-class of the first class, and the sub-class of the sub-class of the first class are hierarchically indicative of the intent of the user.
Hierarchical Methods And Apparatus For Extracting User Intent From Spoken Utterances
US Patent:
2014009, Apr 3, 2014
Filed:
Oct 1, 2013
Appl. No.:
14/043647
Inventors:
- Burlington MA, US
Joseph Simon Reisinger - The Woodlands TX, US
Roberto Sicconi - Danbury CT, US
Mahesh Viswanathan - Somers NY, US
Joseph Simon Reisinger - The Woodlands TX, US
Roberto Sicconi - Danbury CT, US
Mahesh Viswanathan - Somers NY, US
Assignee:
Nuance Communications, Inc. - Burlington MA
International Classification:
G10L 15/18
US Classification:
704249
Abstract:
Improved techniques are disclosed for permitting a user to employ more human-based grammar (i.e., free form or conversational input) while addressing a target system via a voice system. For example, a technique for determining intent associated with a spoken utterance of a user comprises the following steps/operations. Decoded speech uttered by the user is obtained. An intent is then extracted from the decoded speech uttered by the user. The intent is extracted in an iterative manner such that a first class is determined after a first iteration and a sub-class of the first class is determined after a second iteration. The first class and the sub-class of the first class are hierarchically indicative of the intent of the user, e.g., a target and data that may be associated with the target. The multi-stage intent extraction approach may have more than two iterations. By way of example only, the user intent extracting step may further determine a sub-class of the sub-class of the first class after a third iteration, such that the first class, the sub-class of the first class, and the sub-class of the sub-class of the first class are hierarchically indicative of the intent of the user.
Public records
Vehicle Records
Joseph Reisinger
Address:
198 S Cochrans Grn Cir, Spring, TX 77381
VIN:
1HGFA15507L102300
Make:
HONDA
Model:
CIVIC
Year:
2007
NOTICE: You may not use BackgroundCheck or the information it provides to make decisions about employment, credit, housing or any other purpose that would require Fair Credit Reporting Act (FCRA) compliance. BackgroundCheck is not a Consumer Reporting Agency (CRA) as defined by the FCRA and does not provide consumer reports.