Events Calendar

ACL2014 Practice Talk: Kneser- Ney Smoothing on Expected Counts

Speaker: Hui Zhang, USC/ISI

Talk Title: Kneser- Ney Smoothing on Expected Counts

Abstract: Widely used in speech and language processing, Kneser-Ney (KN) smoothing has consistently been shown to be one of the best-performing smoothing methods. However, KN smoothing assumes integer counts, limiting its potential uses—for example, inside Expectation-Maximization. In this paper, we propose a generaliza- tion of KN smoothing that operates on fractional counts, or, more precisely, on distributions over counts. We rederive all the steps of KN smoothing to operate on count distributions instead of integral counts, and apply it to two tasks where KN smoothing was not applicable before: one in language model adaptation, and the other in word alignment. In both cases, our method improves performance significantly.

Biography: Hui Zhang is a fourth year PhD student working with Professor David Chiang at the USC Information Sciences Institute. His main research interests are in statistical machine translation and machine learning.
He has focused on domain adaptation and smoothing techniques.

Home Page:

https://sites.google.com/site/zhangh1982/

Host: Yang Gao

More Info: http://nlg.isi.edu/nl-seminar/

Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey

Audiences: Everyone Is Invited

Contact: Peter Zamar

Event Link: http://nlg.isi.edu/nl-seminar/