Next: Contributions to the objectives of ONR Home: Back to GraphLing Home Page
Next: Contributions to the objectives of ONR
Home: Back to GraphLing Home Page
A Postscript version of this paper is available.
In this work, we will develop probabilistic classifiers for two challenging and diverse natural language processing (NLP) tasks using a common set of techniques. One classifier will be capable of disambiguating a large vocabulary of words with respect to full sets of sense distinctions from published sources, e.g., Longman's on-line dictionary. The second will perform a discourse processing task that involves segmentation, reference resolution, and belief: segmenting a text into blocks that express the beliefs and opinions of a single agent, and identifying noun phrases that refer to that agent. Both systems will be fully automatic.
Exploiting recent developments in applied statistics, we will use a richer class of statistical models than previously used in NLP, along with a set of tools for (1) fitting such models to the data, (2) estimating the parameters of the chosen model from untagged data, (3) and resolving interdependent ambiguities. Together, these techniques will make it computationally feasible to automatically develop and apply probabilistic models that express a more complex set of relationships between a diverse set of variables. This work will advance statistical NLP toward expressing and using the types of knowledge typically thought to be necessary for high-level NLP tasks.