Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Paulo R. Cavalin"'
Publikováno v:
IJCNN
In this work we present a multi-criteria multi-engine approach for text simplification. The main goal is to demonstrate a way to take advantage of a pool of systems, since in the literature several systems have been proposed for the task, and the res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::260520cc666d5936fb969958bfa0ea98
https://doi.org/10.1109/ijcnn52387.2021.9533365
https://doi.org/10.1109/ijcnn52387.2021.9533365
Autor:
Paulo R. Cavalin, Julio Nogima, Victor Henrique Alves Ribeiro, Henrique Ferreira, Claudio S. Pinhanez, Marisa Vasconcelos
Publikováno v:
IJCNN
Chatbots have received significant attention in the last years. These systems have improved operational efficiency by reducing the cost of customer service and more and more are used in customer service channels. More recently, with the addition of s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bc3c2747f00d275d39b257d8a73a98e1
https://doi.org/10.1109/ijcnn52387.2021.9534090
https://doi.org/10.1109/ijcnn52387.2021.9534090
Autor:
Claudio S. Pinhanez, Julio Nogima, Melina Alberio Guerra, Heloisa Candello, Mauro Carlos Pichiliani, Paulo R. Cavalin, Ana Paula Appel, Gabriel Louzada Malfatti, Henrique Ferreira, Victor Henrique Alves Ribeiro, Maíra Gatti de Bayser
Publikováno v:
CHI
This paper describes how machine learning training data and symbolic knowledge from curators of conversational systems can be used together to improve the accuracy of those systems and to enable better curatorial tools. This is done in the context of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb86ae663d0153f9ed0d77bf05d217e3
https://doi.org/10.1145/3411764.3445368
https://doi.org/10.1145/3411764.3445368
Autor:
Heloisa Candello, Claudio S. Pinhanez, Paulo R. Cavalin, Maíra Gatti de Bayser, Mauro Carlos Pichiliani, Ana Paula Appel, Gabriel Louzada Malfatti, Julio Nogima, Henrique Ferreira, Melina Alberio Guerra, Victor Henrique Alves Ribeiro
Publikováno v:
ACL/IJCNLP (1)
In this paper we explore the improvement of intent recognition in conversational systems by the use of meta-knowledge embedded in intent identifiers. Developers often include such knowledge, structure as taxonomies, in the documentation of chatbots.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9405b78168a5c135412137d3257cd875
https://doi.org/10.18653/v1/2021.acl-long.545
https://doi.org/10.18653/v1/2021.acl-long.545
Publikováno v:
CIU
If an artwork could talk, what would visitors ask? This paper explores what types of content voice-based AI conversational systems should have to attend visitors' expectations in a museum. The study analyses 142,463 conversation logs from 5,242 uniqu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3db43cc9a650003097e9097fb433e260
https://doi.org/10.1145/3405755.3406128
https://doi.org/10.1145/3405755.3406128
Autor:
Helon Vicente Hultmann Ayala, Paulo R. Cavalin, Victor Henrique Alves Ribeiro, Gilberto Reynoso-Meza, Pedro Henrique Domingues, Luis Fernando Alzuguir Azevedo
Publikováno v:
IJCNN
Illegal tapping of fuel pipelines has recently become one of the most relevant safety problems faced by the industry. Hundreds of illegal interventions have been reported around the world, causing a significant number of deaths, relevant impacts on t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5a941b4b83a7636bd8b7e06da0052e9e
https://doi.org/10.1109/ijcnn48605.2020.9206602
https://doi.org/10.1109/ijcnn48605.2020.9206602
Publikováno v:
IJCNN
We present a methodology to use Twitter posts to create a parallel corpus which can be used to train Seq2Seq neural networks for a tone rephrasing task. Given that people tend to post texts expressing opinions or emotions of varied intensities regard
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9be802ee8b8f5c48af543f51b451b53f
https://doi.org/10.1109/ijcnn48605.2020.9207298
https://doi.org/10.1109/ijcnn48605.2020.9207298
Autor:
Claudio S. Pinhanez, Paulo R. Cavalin, Marisa Vasconcelos, Victor Henrique Alves Ribeiro, Marcelo Grave
Publikováno v:
EMNLP (Findings)
We present a method for creating parallel data to train Seq2Seq neural networks for sentiment transfer. Most systems for this task, which can be viewed as monolingual machine translation (MT), have relied on unsupervised methods, such as Generative A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac6ccc5ec5a6679c5bc4bfa9331a9341
https://doi.org/10.18653/v1/2020.findings-emnlp.61
https://doi.org/10.18653/v1/2020.findings-emnlp.61
Publikováno v:
EMNLP (1)
This paper explores how intent classification can be improved by representing the class labels not as a discrete set of symbols but as a space where the word graphs associated to each class are mapped using typical graph embedding techniques. The app
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::deb6e4c4d31ac407f218e502ea7a9d4e
https://doi.org/10.18653/v1/2020.emnlp-main.324
https://doi.org/10.18653/v1/2020.emnlp-main.324
Autor:
Flavio Figueiredo, Marisa Vasconcelos, Mauro Carlos Pichiliani, Heloisa Candello, Haylla Do Carmo, Paulo R. Cavalin, Claudio S. Pinhanez
Publikováno v:
Anais Estendidos do Simpósio Brasileiro de Fatores Humanos em Sistemas Computacionais (IHC).
Como a presença de audiência influencia a interação social com um sistema conversacional em um espaço físico? Para responder a essa questão, esta pesquisa analisou dados de uma exposição de arte em que os visitantes interagiam em linguagem n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd157a8ed3bb166715b47cc12f795d5f
https://doi.org/10.5753/ihc.2019.8425
https://doi.org/10.5753/ihc.2019.8425