A Connectionist Thematic Grid Predictor for Pre-parsed Natural Language Sentences

Authors:
João Luís Rosa
Affiliations:
Computer Engineering Faculty - Ceatec, Pontifical Catholic University of Campinas - PUC-Campinas, Campinas, São Paulo, Brazil
Venue:
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Year:
2007

Citing 8
Cited 1

Mechanisms of sentence processing: assigning roles to constituents

Parallel distributed processing: explorations in the microstructure of cognition, vol. 2
Episodic logic meets Little Red Riding Hood: a comprehensive natural representation for language understanding

Natural language processing and knowledge representation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Automatic labeling of semantic roles

Computational Linguistics
A Biologically Inspired Connectionist System for Natural Language Processing

SBRN '02 Proceedings of the VII Brazilian Symposium on Neural Networks (SBRN'02)
Empirical acquisition of conceptual distinctions via dictionary definitions

Empirical acquisition of conceptual distinctions via dictionary definitions
Biologically plausible error-driven learning using local activation differences: The generalized recirculation algorithm

Neural Computation

SABIO: A BIOLOGICALLY PLAUSIBLE CONNECTIONIST APPROACH TO AUTOMATIC TEXT SUMMARIZATION

Applied Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Inspired on psycholinguistics and neuroscience, a symbolic-connectionist hybrid system called 茂戮驴-Pred(ThematicPredictor for natural language) is proposed, designed to reveal the thematic grid assigned to a sentence. Through a symbolic module, which includes anaphor resolution and relative clause processing, a parsing of the input sentence is performed, generating logical formulae based on events and thematic roles for Portuguese language sentences. Previously, a morphological analysis is carried out. The parsing displays, for grammatical sentences, the existing readings and their thematic grids. In order to disambiguate among possible interpretations, there is a connectionist module, comprising, as input, a featural representation of the words (based on verb/noun WordNetclassification and on classical semantic microfeature representation), and, as output, the thematic grid assigned to the sentence. 茂戮驴-Predemploys biologically inspired training algorithm and architecture, adopting a psycholinguistic view of thematic theory.