Paper: A Pylonic Decision-Tree Language Model With Optimal Question Selection

ACL ID P99-1080
Title A Pylonic Decision-Tree Language Model With Optimal Question Selection
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1999
Authors

This paper discusses a decision-tree approach to the problem of assigning probabilities to words following a given text. In contrast with previ- ous decision-tree language model attempts, an algorithm for selecting nearly optimal questions is considered. The model is to be tested on a standard task, The Wall Street Journal, allow- ing a fair comparison with the well-known tri- gram model.