Grammatical Heads Optimized for Parsing and Their Comparison with Linguistic Intuition
نویسندگان
چکیده
This paper deals with head-driven chart parsing on large natural-language grammars. We present a procedure that optimizes positions of heads in the grammar rules based on the number of edges in the resulting chart. New performance evaluation tool PACE is briefly introduced first. The head-optimizing procedure is described and the results are given. The last part compares the head positions obtained automatically with those set according to traditional linguistics.
منابع مشابه
A corpus-based connectionist architecture for large-scale natural language parsing
We describe a deterministic shift-reduce parsing model that combines the advantages of connectionism with those of traditional symbolic models for parsing realistic sub-domains of natural language. It is a modular system that learns to annotate natural language texts with syntactic structure. The parser acquires its linguistic knowledge directly from pre-parsed sentence examples extracted from ...
متن کاملLearning Syntactic Rules and Tags with Genetic Algorithms for Information Retrieval and Filtering: An Empirical Basis for Grammatical Rules
The grammars of natural languages may be learned by using genetic algorithms that reproduce and mutate grammatical rules and part-of-speech tags, improving the quality of later generations of grammatical components. Syntactic rules are randomly generated and then evolve; those rules resulting in improved parsing and occasionally improved retrieval and filtering performance are allowed to furthe...
متن کاملAn improved joint model: POS tagging and dependency parsing
Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipel...
متن کاملDatabase Oriented Chart Parsing
We introduce the notion of parsing and translation using Database technology. The framework focuses on the notion of “Database Oriented parsing”. We describe the basic notion of linguistic representation using relational tables in SQL and we specify a set of operators on these tables for parsing and translation. The framework provides a flexible mechanism for modeling cross linguistic informati...
متن کاملGrammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
This paper is concerned with building linguistic resources and statistical parsers for deep grammatical relation (GR) analysis of Chinese texts. A set of linguistic rules is defined to explore implicit phrase structural information and thus build high-quality GR annotations that are represented as general directed dependency graphs. The reliability of this linguistically-motivated GR extraction...
متن کامل