The concept of maximum entropy can be traced back along multiple threads to Biblical
times. Only recently, however, have computers become powerful enough to permit the …

In many real-world learning tasks, it is expensive to acquire a sufficient number of labeled
examples for training. This paper proposes a general method for efficiently training …

We present an implementation of a part-of-speech tagger based on a hidden Markov model.
The methodology enables robust and accurate tagging with few resource requirements …

After presenting a novel O (n^ 3) parsing algorithm for dependency grammar, we develop
three contrasting ways to stochasticize it. We propose (a) a lexical affinity model where …

A system for part-of-speech tagging is described. It is based on a hidden Markov model
which can be trained using a corpus of untagged text. Several techniques are introduced to …

Most recent research in trainable part of speech taggers has explored stochastic tagging.
While these taggers obtain high accuracy, linguistic information is captured indirectly …

Experiments show that the best training is obtained by using as much tagged text as
possible. They also show that Maximum Likelihood training, the procedure that is routinely …

The 1990s have witnessed a resurgence of interest in 1950s-style empirical and statistical
methods of language analysis. Empiricism was at its peak in the 1950s, dominating a broad …

This paper presents a statistical decision procedure for lexical ambiguity resolution. The
algorithm exploits both local syntactic patterns and more distant collocational evidence …

We describe a statistical technique for assigning senses to words. An instance of a word is
assigned a sense by asking a question about the context in which the word appears. The …