2010 Poster Sessions : SMS Text Normalization using Statistical Machine Translation

Student Name : Stefan Krawczyk , Karthik Raghunathan
Advisor : Chris Manning
Research Areas: Artificial Intelligence
Abstract:
Short Message Service (SMS) text normalization is the task of translating the informal language used in SMS messages into normal English. It is a challenging problem since text messages can be highly polysemous, and different geographical locales use different deletions, abbreviations, phonetic contractions and colloquial terms. We pose this problem as a statistical machine translation (SMT) task and present a usable system (available as a web service) whose performance is comparable with the state-of-the-art.

Bios:
Karthik Raghunathan is a second year Computer Science Masters student specializing in Artificial Intelligence at Stanford University. He works as a graduate research assistant in the Stanford Natural Language Processing Group under Prof. Christopher Manning.
Prior to joining Stanford, Karthik got his Bachelor of Technology (B.Tech) degree in Computer Science and Engineering from the National Institute of Technology, Calicut in India. His research interests include Artificial Intelligence, especially Natural Language Processing and its applications to intelligent human-machine interaction.

Stefan Krawczyk is a second year Computer Science Masters student specializing in Artificial Intelligence. Stefan currently works as a graduate research assistant in the Natural Language Processing Group under Prof. Dan Jurafsky.
Prior to Stanford, Stefan worked at IBM in San Jose after finishing his undergraduate degree with first class honours in Computer Science from Victoria University of Wellington, New Zealand.