Geometric algebra rotors for sub-symbolic coding of natural language sentences

Authors:
Giovanni Pilato;Agnese Augello;Giorgio Vassallo;Salvatore Gaglio
Affiliations:
Italian National Research Council, Palermo, Italy;DINFO, University of Palermo, Palermo, Italy;DINFO, University of Palermo, Palermo, Italy;Italian National Research Council, Palermo, Italy and DINFO, University of Palermo, Palermo, Italy
Venue:
KES'07/WIRN'07 Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part I
Year:
2007

Citing 8
Cited 0

Language Modeling for Information Retrieval

Language Modeling for Information Retrieval
Learning question classifiers

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
A Sub-Symbolic Approach to Word Modelling for Domain Specific Speech Recognition

CAMP '05 Proceedings of the Seventh International Workshop on Computer Architecture for Machine Perception
Text Representation: From Vector to Tensor

ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Automatic evaluation of students' answers using syntactically enhanced LSA

HLT-NAACL-EDUC '03 Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing - Volume 2
Sentence Similarity Based on Semantic Nets and Corpus Statistics

IEEE Transactions on Knowledge and Data Engineering
Non-contiguous word sequences for information retrieval

MWE '04 Proceedings of the Workshop on Multiword Expressions: Integrating Processing
Subtree mining for question classification problem

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A sub-symbolic encoding methodology for natural language sentences is presented. The procedure is based on the creation of an LSA-inspired semantic space and associates rotation operators derived from Geometric Algebra to word bigrams of the sentence. The operators are subsequently applied to an orthonormal standard basis of the created semantic space according to the order in which words appear in the sentence. The final rotated basis is then coded as a vector and its orthogonal part constitutes the sub-symbolic coding of the sentence. Preliminary experimental results for a classification task, compared with the traditional LSA methodology, show the effectiveness of the approach.