Sentence comparison using robust minimal recursion semantics and an ontology

Authors:
Rebecca Dridan;Francis Bond
Affiliations:
The University of Melbourne;Nippon Telegraph and Telephone Corporation
Venue:
LD '06 Proceedings of the Workshop on Linguistic Distances
Year:
2006

Citing 5
Cited 1

Efficient deep processing of Japanese

COLING '02 Proceedings of the 3rd workshop on Asian language resources and international standardization - Volume 12
Japanese dependency analysis using cascaded chunking

COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Dependency-based sentence alignment for multiple document summarization

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Constraint-based RMRS construction from shallow grammars

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Robust ontology acquisition from machine-readable dictionaries

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence

Partial parse selection for robust deep processing

DeepLP '07 Proceedings of the Workshop on Deep Linguistic Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We design and test a sentence comparison method using the framework of Robust Minimal Recursion Semantics which allows us to utilise the deep parse information produced by Jacy, a Japanese HPSG based parser and the lexical information available in our ontology. Our method was used for both paraphrase detection and also for answer sentence selection for question answering. In both tasks, results showed an improvement over Bag-of-Words, as well as providing extra information useful to the applications.