Many problems in computational linguistics are well suited for bootstrapping (semisupervised learning) techniques. The Yarowsky algorithm is a well-known bootstrapping algorithm, but it is not mathematically well understood. This article analyzes it as optimizing an objective function. More specifically, a number of variants of the Yarowsky algorithm (though not the original algorithm itself) are shown to optimize either likelihood or a closely related objective function K.

This paper refines the analysis of co-training, defines and evaluates a new co-training algorithm that has theoretical justification, gives a theoretical justification for the Yarowsky algorithm, and shows that co-training and the Yarowsky algorithm are based on different independence assumptions.

The prediction of intonational phrase boundaries from raw text is an important step for a text-to-speech system: locating where to place short pauses enables more natural sounding speech, that can be more easily understood. We improved upon earlier work [Hirschberg and Prieto, 1996] by adding syntactic information gained from a high-accuracy parser [Collins, 1999]. We report significant improvement using various experimental setups. We also show that our improved method comes close to interannotator agreement.

Both probabilistic context-free grammars (PCFGs) and shift-reduce probabilistic pushdown automata (PPDAs) have been used for language modeling and maximum likelihood parsing. We investigate the precise relationship between these two formalisms, showing that, while they define the same classes of probabilistic languages, they appear to impose different inductive biases.

Finite state cascades represent an attractive architecture for parsing unrestricted text. Deterministic parsers specified by finite state cascades are fast and reliable. They can be extended at modest cost to construct parse trees with finite feature structures. Finally, such deterministic parsers do not necessarily involve trading off accuracy against speed — they may in fact be more accurate than exhaustive search stochastic context free parsers.

In this paper, we introduce ephemeral interest groups for supporting informal communication. Ephemeral interest groups are electronic discussion groups that, in contrast to bulletin boards and the like, are short-lived and ad hoc. They are designed as a medium for informal discussions of items broadcast to a wider community. We have implemented a prototype system to explore ephemeral interest groups. We discuss the goals of the system, characterize its evolution over the last ten months of deployment, and sketch our plans for future developments.