Probabilistic Parsing of Unrestricted English Text, With a I-Iighly-Detailed Grammar.

Summary A grammar-based probabilistic parser is described, and experimental results are pre- sented for the parser as trained and tested on a 676,000-word, highly varied treebank of unrestricted English text. Probabilistic decision trees are utilized as a means of prediction, and a grammar with about 3000 semantic-and-syntactic tags, and 1100 non-terminal node labels suppl/es detailed lingzdstic information. Further such data is supplied for prediction purposes by thousands of questions about "raw" words, expres~ sions, and the sentence as a whole. The rich/n.formation base used for parse prediction allows the system to parse in a domain-general, totally--open-vocabulary setting, and to output highly-detailed semantic as well as syntactic information for sentences pro- ccessed. Finally, a statistical procedure is described for converting less-detailed into more--detailed treebank, for use in increasing parser accuracy via much larger training treeb~.nlc~.