Sub-Symbolic Knowledge Representation for Evocative Chat-bots

Salvatore Gaglio, Giorgio Vassallo, Agnese Augello, Salvatore Gaglio, Giovanni Pilato

Risultato della ricerca: Chapter

Abstract

The proposed work illustrates how “primitive concepts” can be automatically induced from a text corpus. The pri- mitive concepts are identified by the orthonormal axis of a “conceptual” space induced by a methodology inspired to the Latent Semantic Analysis approach. The methodology represents a natural language sentence by means of a set of rotations of an orthonormal basis in the “conceptual” space. The rotations, triggered by the sequence of words composing the sentence and realized by means of Geomet- ric Algebra rotors, allow to highlight “conceptual” rela- tions that can arise among the primitive concepts.
Lingua originaleEnglish
Titolo della pubblicazione ospiteInterdisciplinary Aspects of Information Systems Studies
Pagine343-349
Numero di pagine6
Stato di pubblicazionePublished - 2008

Fingerprint

Knowledge representation
Latent semantic analysis
Methodology
Language

All Science Journal Classification (ASJC) codes

  • Economics, Econometrics and Finance(all)
  • Business, Management and Accounting(all)

Cita questo

Gaglio, S., Vassallo, G., Augello, A., Gaglio, S., & Pilato, G. (2008). Sub-Symbolic Knowledge Representation for Evocative Chat-bots. In Interdisciplinary Aspects of Information Systems Studies (pagg. 343-349)

Sub-Symbolic Knowledge Representation for Evocative Chat-bots. / Gaglio, Salvatore; Vassallo, Giorgio; Augello, Agnese; Gaglio, Salvatore; Pilato, Giovanni.

Interdisciplinary Aspects of Information Systems Studies. 2008. pag. 343-349.

Risultato della ricerca: Chapter

Gaglio, S, Vassallo, G, Augello, A, Gaglio, S & Pilato, G 2008, Sub-Symbolic Knowledge Representation for Evocative Chat-bots. in Interdisciplinary Aspects of Information Systems Studies. pagg. 343-349.
Gaglio S, Vassallo G, Augello A, Gaglio S, Pilato G. Sub-Symbolic Knowledge Representation for Evocative Chat-bots. In Interdisciplinary Aspects of Information Systems Studies. 2008. pag. 343-349
Gaglio, Salvatore ; Vassallo, Giorgio ; Augello, Agnese ; Gaglio, Salvatore ; Pilato, Giovanni. / Sub-Symbolic Knowledge Representation for Evocative Chat-bots. Interdisciplinary Aspects of Information Systems Studies. 2008. pagg. 343-349
@inbook{ec59deed12144b7d98efce5d1602d21a,
title = "Sub-Symbolic Knowledge Representation for Evocative Chat-bots",
abstract = "The proposed work illustrates how “primitive concepts” can be automatically induced from a text corpus. The pri- mitive concepts are identified by the orthonormal axis of a “conceptual” space induced by a methodology inspired to the Latent Semantic Analysis approach. The methodology represents a natural language sentence by means of a set of rotations of an orthonormal basis in the “conceptual” space. The rotations, triggered by the sequence of words composing the sentence and realized by means of Geomet- ric Algebra rotors, allow to highlight “conceptual” rela- tions that can arise among the primitive concepts.",
author = "Salvatore Gaglio and Giorgio Vassallo and Agnese Augello and Salvatore Gaglio and Giovanni Pilato",
year = "2008",
language = "English",
isbn = "978-3-7908-2009-6",
pages = "343--349",
booktitle = "Interdisciplinary Aspects of Information Systems Studies",

}

TY - CHAP

T1 - Sub-Symbolic Knowledge Representation for Evocative Chat-bots

AU - Gaglio, Salvatore

AU - Vassallo, Giorgio

AU - Augello, Agnese

AU - Gaglio, Salvatore

AU - Pilato, Giovanni

PY - 2008

Y1 - 2008

N2 - The proposed work illustrates how “primitive concepts” can be automatically induced from a text corpus. The pri- mitive concepts are identified by the orthonormal axis of a “conceptual” space induced by a methodology inspired to the Latent Semantic Analysis approach. The methodology represents a natural language sentence by means of a set of rotations of an orthonormal basis in the “conceptual” space. The rotations, triggered by the sequence of words composing the sentence and realized by means of Geomet- ric Algebra rotors, allow to highlight “conceptual” rela- tions that can arise among the primitive concepts.

AB - The proposed work illustrates how “primitive concepts” can be automatically induced from a text corpus. The pri- mitive concepts are identified by the orthonormal axis of a “conceptual” space induced by a methodology inspired to the Latent Semantic Analysis approach. The methodology represents a natural language sentence by means of a set of rotations of an orthonormal basis in the “conceptual” space. The rotations, triggered by the sequence of words composing the sentence and realized by means of Geomet- ric Algebra rotors, allow to highlight “conceptual” rela- tions that can arise among the primitive concepts.

UR - http://hdl.handle.net/10447/48093

M3 - Chapter

SN - 978-3-7908-2009-6

SP - 343

EP - 349

BT - Interdisciplinary Aspects of Information Systems Studies

ER -

Accesso al documento