An Approach to Enhance Chatbot Semantic Power and Maintainability: Experiences within the FRASI Project

Salvatore Gaglio, Alberto Machi, Agnese Augello, Giovanni Pilato, Agnese Augello

Risultato della ricerca: Other

13 Citazioni (Scopus)

Abstract

The paper illustrates the implementation and semantic enhancement of a domain-oriented Question-Answering system based on a pattern-matching chat bot technology, developed within an industrial project, named FRASI. The main difficulty in building a KB for a chat bot is to handwrite all possible question-answer pairs that constitute the KB. The proposed approach simplifies the chat bot realization thanks to two solutions. The first one uses an ontology, which is exploited in a twofold manner: to construct dynamic answers as a result of an inference process about the domain, and to automatically populate, off-line, the chat bot KB with sentences that can be derived from the ontology, describing properties and relations between concepts involved in the dialogue. The second one is to preprocess user sentences, and to reduce them to a simpler structure that can be referred to existing elements of the chat bot KB. The enhanced symbolic reduction of user questions and the automatic population of question templates in the chat bot KB from domain ontology have been implemented as two computational services (external modules).
Lingua originaleEnglish
Pagine186-193
Numero di pagine8
Stato di pubblicazionePublished - 2012

Fingerprint

Maintainability
Ontology
Semantics
Pattern matching

All Science Journal Classification (ASJC) codes

  • Software

Cita questo

An Approach to Enhance Chatbot Semantic Power and Maintainability: Experiences within the FRASI Project. / Gaglio, Salvatore; Machi, Alberto; Augello, Agnese; Pilato, Giovanni; Augello, Agnese.

2012. 186-193.

Risultato della ricerca: Other

Gaglio, Salvatore ; Machi, Alberto ; Augello, Agnese ; Pilato, Giovanni ; Augello, Agnese. / An Approach to Enhance Chatbot Semantic Power and Maintainability: Experiences within the FRASI Project. 8 pag.
@conference{1f8cc8171b4f418497ab2807d385e93f,
title = "An Approach to Enhance Chatbot Semantic Power and Maintainability: Experiences within the FRASI Project",
abstract = "The paper illustrates the implementation and semantic enhancement of a domain-oriented Question-Answering system based on a pattern-matching chat bot technology, developed within an industrial project, named FRASI. The main difficulty in building a KB for a chat bot is to handwrite all possible question-answer pairs that constitute the KB. The proposed approach simplifies the chat bot realization thanks to two solutions. The first one uses an ontology, which is exploited in a twofold manner: to construct dynamic answers as a result of an inference process about the domain, and to automatically populate, off-line, the chat bot KB with sentences that can be derived from the ontology, describing properties and relations between concepts involved in the dialogue. The second one is to preprocess user sentences, and to reduce them to a simpler structure that can be referred to existing elements of the chat bot KB. The enhanced symbolic reduction of user questions and the automatic population of question templates in the chat bot KB from domain ontology have been implemented as two computational services (external modules).",
author = "Salvatore Gaglio and Alberto Machi and Agnese Augello and Giovanni Pilato and Agnese Augello",
year = "2012",
language = "English",
pages = "186--193",

}

TY - CONF

T1 - An Approach to Enhance Chatbot Semantic Power and Maintainability: Experiences within the FRASI Project

AU - Gaglio, Salvatore

AU - Machi, Alberto

AU - Augello, Agnese

AU - Pilato, Giovanni

AU - Augello, Agnese

PY - 2012

Y1 - 2012

N2 - The paper illustrates the implementation and semantic enhancement of a domain-oriented Question-Answering system based on a pattern-matching chat bot technology, developed within an industrial project, named FRASI. The main difficulty in building a KB for a chat bot is to handwrite all possible question-answer pairs that constitute the KB. The proposed approach simplifies the chat bot realization thanks to two solutions. The first one uses an ontology, which is exploited in a twofold manner: to construct dynamic answers as a result of an inference process about the domain, and to automatically populate, off-line, the chat bot KB with sentences that can be derived from the ontology, describing properties and relations between concepts involved in the dialogue. The second one is to preprocess user sentences, and to reduce them to a simpler structure that can be referred to existing elements of the chat bot KB. The enhanced symbolic reduction of user questions and the automatic population of question templates in the chat bot KB from domain ontology have been implemented as two computational services (external modules).

AB - The paper illustrates the implementation and semantic enhancement of a domain-oriented Question-Answering system based on a pattern-matching chat bot technology, developed within an industrial project, named FRASI. The main difficulty in building a KB for a chat bot is to handwrite all possible question-answer pairs that constitute the KB. The proposed approach simplifies the chat bot realization thanks to two solutions. The first one uses an ontology, which is exploited in a twofold manner: to construct dynamic answers as a result of an inference process about the domain, and to automatically populate, off-line, the chat bot KB with sentences that can be derived from the ontology, describing properties and relations between concepts involved in the dialogue. The second one is to preprocess user sentences, and to reduce them to a simpler structure that can be referred to existing elements of the chat bot KB. The enhanced symbolic reduction of user questions and the automatic population of question templates in the chat bot KB from domain ontology have been implemented as two computational services (external modules).

UR - http://hdl.handle.net/10447/74852

M3 - Other

SP - 186

EP - 193

ER -