Paper: Ambiguity Packing In Constraint-Based Parsing Practical Results

ACL ID A00-2022
Title Ambiguity Packing In Constraint-Based Parsing Practical Results
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2000

We describe a novel approach to 'packing' of local am- biguity in parsing with a wide-coverage HPSG gram- mar, and provide an empirical assessment of the in- teraction between various packing and parsing strate- gies. We present a linear-time, bidirectional subsump- tion test for typed feature structures and demonstrate that (a) subsumption- and equivalence-based packing is applicable to large HPSG grammars and (b) average parse complexity can be greatly reduced in bottom-up chart parsing with comprehensive HPSG implementations. 1 Background The ambiguity inherent in natural language means that during parsing, some segments of the input string may end up being analysed as the same type of linguistic object in several different ways. Each of these different ways must be recorded, but subse-...