Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Fusion of knowledge-based and data-driven approaches to grammar induction

Petrakis Evripidis, Potamianos Alexandros, Cimiano, Philipp 1977-, Walter Sebastian , Iosif Ilias, Unger Christina , Georgiladakis Spyridon

Full record


URI: http://purl.tuc.gr/dl/dias/218602D8-36D9-49B1-AD72-F229295EDB93
Year 2014
Type of Item Conference Full Paper
License
Details
Bibliographic Citation S. Georgiladakis, Ch. Unger, E. Iosif, S. Walter, Ph. Cimiano, E. Petrakis and A. Potamianos, "Fusion of knowledge-based and data-driven approaches to grammar induction," presented at 15th Annual Conference of the International Speech Communication Association, Singapore, 2014.
Appears in Collections

Summary

Using different sources of information for grammar induction results in grammars that vary in coverage and precision. Fusing such grammars with a strategy that exploits their strengths while minimizing their weaknesses is expected to produce grammars with superior performance. We focus on the fusion of grammarsproduced using a knowledge-based approach using lexicalized ontologies and a data-driven approach using semantic similarity clustering. We propose various algorithms for finding the mapping between the (non-terminal) rules generated by each grammar induction algorithm, followed by rule fusion. Three fusion approaches are investigated: early, mid and late fusion. Results show that late fusion provides the best relative F-measure performance improvement by 20%.

Services

Statistics