Year: 2005
Type: conference-paper
Abstract: We present a novel approach for applying the Inside-Outside Algorithm to a packed parse forest produced by a unificationbased parser.The approach allows a node in the forest to be assigned multiple inside and outside probabilities, enabling a set of 'weighted GRs' to be computed directly from the forest.The approach improves on previous work which either loses efficiency by unpacking the parse forest before extracting weighted GRs, or places extra constraints on which nodes can be packed, leading to less compact forests.Our experiments demonstrate substantial increases in parser accuracy and throughput for weighted GR output.
Authors: Rebecca Watson, John Carroll, Ted Briscoe
Institutions: University of Cambridge, University of Sussex
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funder: Cambridge Commonwealth Trust
OpenAlex ID: W2113349888