Heuristics for Broad-Coverage Natural Language Parsing

HEURISTICS FOR BROAD-COVERAGE NATURAL LANGUAGE PARSING Michael C. McCord IBM T. J. Watson Research Center POB 704 Yorktown Heights, NY 10598 ABSTRACT The Slot Grammar system is interesting for natural language applica- tions because it can deliver parses with deep grammatical information on a reasonably broad scale. The paper describes a numerical scoring system used in Slot Grammar for ambiguity resolution, which not only ranks parses but also contributes to parsing efficiency through a parse space pruning algorithm. Details of the method of computing parse scores are given, and test results for the English Slot Grammar are presented. 1. INTRODUCTION As everyone who has tried it knows, the hardest part of build- ing a broad-coverage parser is not simply covering all the constructions of the language, but dealing with ambiguity. One approach to ambiguity resolution is to "understand" the text well enough - to have a good semantic interpretation system, to use real-world modeling, inference, etc. This can work well in small domains, and it is, in this author's opin- ion, ultimately necessary for the highest quality of natural language processing in any domain; but it is probably not feasible on a broad scale today. So some kind of heuristic method is needed for disambiguation, some way of ranking analyses and choosing the best. Even in the ideal model of human language processing (which would use a great deal of knowledge representation and inference), ranking heuristics seem appropriate as a mechanism since humans must work with incomplete knowledge most of the time. Two major questions that can be asked about a heuristic method for ambiguity resolution are these: 1. What level of representation is used for disambiguation and is involved in the statements of the heuristic rules - lexical/morphological, surface syntactic, deep syntactic, or logical/semantic? 2. Where do the heuristic rules come from? Are they largely created through human linguistic insight, or are they induced by processing corpora? This paper describes the heuristic method used in the Slot Grammar (SG)system [10, 11, 13, 16, 17] for ambiguity res- olution - the SG parse scoring system. This scoring system operates during parsing (with a bottom-up chart parser), as- signing real number scores to partial analyses as well as to analyses of the complete sentence. The scores are used not only for ranking the final analyses but also for pruning the parse space during parsing, thus increasing time and space efficiency. The level of representation being disambiguated is thus the level of SG parses. SG parse structures are dependency- or head-oriented, and include, in a single tree, both surface structure and deep syntactic information such as predicate- argument structure, remote dependencies, control informa- tion, and unwinding of passives. 1 SG parse structures also include a choice of word senses. The extent to which these represent semantic sense distinctions depends on the lexicon. The SG system is set up to deal with semantic word-sense distinctions and to resolve them by doing semantic type-checking during parsing. However, in the lexicon for ESG (English Slot …

Content truncated to 500 words