SearcharxivSearch

arXiv subjects

John Larcheveque

Publications and source records attributed to John Larcheveque.

2 recordsLinked to original sources

Graph Interpolation Grammars as Context-Free Automata

A derivation step in a Graph Interpolation Grammar has the effect of scanning an input token. This feature, which aims at emulating the incrementality of the natural parser, restricts the formal power of GIGs. This contrasts with the fact that the derivation mechanism involves a context-sensitive device similar to tree adjunction in TAGs. The combined effect of input-driven derivation and restricted context-sensitiveness would be conceivably unfortunate if it turned out that Graph Interpolation Languages did not subsume Context Free Languages while being partially context-sensitive. This report sets about examining relations between CFGs and GIGs, and shows that GILs are a proper superclass of CFLs. It also brings out a strong equivalence between CFGs and GIGs for the class of CFLs. Thus, it lays the basis for meaningfully investigating the amount of context-sensitiveness supported by GIGs, but leaves this investigation for further research.

cmp-lg

Graph Interpolation Grammars: a Rule-based Approach to the Incremental Parsing of Natural Languages

Graph Interpolation Grammars are a declarative formalism with an operational semantics. Their goal is to emulate salient features of the human parser, and notably incrementality. The parsing process defined by GIGs incrementally builds a syntactic representation of a sentence as each successive lexeme is read. A GIG rule specifies a set of parse configurations that trigger its application and an operation to perform on a matching configuration. Rules are partly context-sensitive; furthermore, they are reversible, meaning that their operations can be undone, which allows the parsing process to be nondeterministic. These two factors confer enough expressive power to the formalism for parsing natural languages.

cmp-lg