A Maximum Entropy Approach to Natural Language Processing
Berger et al., 1996, A Maximum Entropy Approach to Natural Language Processing (Computational Linguistics)
Subscriber deck — free during early access
1 cards in “1 Introduction” · whole deck
1 Introduction
- What are the two essential tasks of statistical modeling, according to Berger et al.?Feature selection (determining a set of statistics that capture the behavior of a random process) and model selection (corralling those facts into an accurate predictive model). Maximum entropy gives a unified approach to both.
- Berger et al., 1996, A Maximum Entropy Approach to Natural Language Processing (Computational Linguistics), §1
Source
- Adam L. Berger, Stephen A. Della Pietra and Vincent J. Della Pietra. 1996. A Maximum Entropy Approach to Natural Language Processing. In Computational Linguistics, pp. 39–71. https://aclanthology.org/J96-1002/