Title :
Two decades of statistical language modeling: where do we go from here?
Author :
Rosenfeld, Ronald
Author_Institution :
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
Statistical language models estimate the distribution of various natural language phenomena for the purpose of speech recognition and other language technologies. Since the first significant model was proposed in 1980, many attempts have been made to improve the state of the art. We review them, point to a few promising directions, and argue for a Bayesian approach to integration of linguistic theories with data.
Keywords :
Bayes methods; computational linguistics; natural languages; probability; reviews; Bayesian approach; linguistic theory; natural language processing; natural language technologies; probability; speech recognition; state of the art; statistical language modeling; Associate members; Bayesian methods; Information retrieval; Natural languages; Optical character recognition software; Paper technology; Probability distribution; Routing; Speech recognition; Training data;
Journal_Title :
Proceedings of the IEEE
