Project and implementation of a personal assistant for meeting scheduling
DOI:
https://doi.org/10.11606/issn.2526-8260.mecatrone.2022.165379Keywords:
Natural Language, Multi-agent Systems, Text ProcessingAbstract
The process of scheduling a meeting relies on a negotiation between two or more actors and might be a tedious task, therefore resulting in unoptimezed results given the lack of commitment of the actors. To solve this problem, it was proposed an assistante based on an architecture with two main modules: Semanticizer, responsible for the natural language processing and the creation of an object that represents the semantic of the user utterance; Dialog Managers, responsible for dialog’s conduction, processing the Semanticizer output and generating outputs. This solution allowed half of the testers to accomplish their goals while using the assistant, with an average of three turns to collect all relevant data to the meeting. It also achieved 84% of accuracy to identify relevant entities and 53% of accuracy to identify relevant intents expressed by the users.
Downloads
References
COGROO. Corretor Gramatical Acoplável ao LibreOffice. Acessado em janeiro de 2019. Disponível em: <http://cogroo.org/>. Citado na página 3.
CORPORA, NLTK. WordNet, a Lexical Database for English. Acessado em janeiro de 2019. Disponível em: https://www.nltk.org/book/ch02.html>. Citado na página 3.
GRUBER, Tom. Ontology. In: . Encyclopedia of Database Systems. Boston, MA: Springer US, 2009. p. 1963–1965. ISBN 978-0-387-39940-9. Disponível em: <https://doi.org/10.1007/978-0-387-39940-9_1318>. Citado na página 3.
HARISPE, Sébastien ; et al. Semantic similarity from natural language and ontology analysis. Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers LLC, v. 8, n. 1, may 2015, 6–20. Disponível em: https://doi.org 10.2200%2Fs00639ed1v01y201504hlt027>. Citado na página 2.
IBM. Watson Assistant. Acessado em janeiro de 2019. Disponível em: <https://www.ibm.com/ cloud/watson-assistant/>. Citado na página 3.
LARIONOV, George ; et al. Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture. arXiv e-prints, [S.l.: s.n.], Dec 2018, arXiv:1812.01260. Citado na página 4.
LEVIATHAN, Yaniv; MATIAS, Yossi. Google Duplex: An AI System for Accomplishing Real-World Tasks Over the Phone. 2019. Disponível em: <https://ai.googleblog.com/2018/05/ duplex-ai-system-for-natural-conversation.html>. Citado na página 1.
RAM, Ashwin ; et al. The science behind the alexa prize. Alexa.Prize.Proceedings, [s.n.], 2018. Disponível em: https://developer.amazon.com/alexaprize/proceedingsaccessed(2018)-01-01>. Citado na página 3.
SATO, Erich; FIGUEIREDO, Nicolas. Sistema de diálogo para agendamento automático de compromissos. [S.l.: s.n.], 2017. Citado na página 5.
SLIMANI, Thabet. Description and evaluation of semantic similarity measures approaches. International Journal of Computer Applications, Foundation of Computer Science, v. 80, n. 10, oct 2013, 25–33. Disponível em: https://doi.org/10.5120%2F13897-1851>. Citado na página 3.
SPACY. Industrial-Strength Natural Language Processing. Acessado em janeiro de 2019. Disponível em: <https://spacy.io/>. Citado na página 3.
WORDNET. WordNet, a Lexical Database for English. Acessado em janeiro de 2019. Disponível em: https://wordnet.princeton.edu/>. Citado na página 3.
XUE NIANWEN, Steven Bird Evan Klein; LOPER, Edward. Natural language processing with python. [S.l.]: O’Reilly Media Inc, n. 3, 2009. Citado na página 3.
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Ricardo Ciriaco Camargo Imagure, Mateus Ramos Vendramini
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
