Name: Presentation: Smoothing Methods with Ajay Bapat
Start: 2013-12-04T18:30:00-07:00
End: 2013-12-04T21:30:00-07:00
Location: Fuse at The Riverside

Abstract:

When modeling language with probabilities an unseen word (i.e. a zero probability) will transform a perfectly good sequence of numbers into a useless one. Smoothing methods present on way to avoid this problem.

In this talk I'll be giving an overview of smoothing methods, with some theory and motivation behind different smoothing methods. The topics I plan on covering are listed below:

• Additive smoothing.

• Estimating probabilities from counts using held-out set and Good-Turing method.

• Jelinek-Mercer smoothing

• Katz Back-off model

• Kneser-Ney model

Presenter Bio:

Ajay Bapat works in the search and data team at a startup in Boulder.

Lee Becker

Greg Brown

Front Range NLP (Natural Language Processing)

Technology

Artificial Intelligence

Database Professionals

Computer Science

Natural Language Processing

Machine Learning

Data Mining

Stefan Codrescu

Hans-Peter Klett

amber

Randall Sparks

Jay Swartz

Anish Parikh

Presentation: Smoothing Methods with Ajay Bapat

Fuse at The Riverside

Share

Front Range NLP (Natural Language Processing)

Presentation: Smoothing Methods with Ajay Bapat

Front Range NLP (Natural Language Processing)

Details

Members are also interested in