11 citations · 13 across the 6 of their papers we have counts for
11 papers
Exploring the Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Out-of-Scope Detection Tasks
Claudio Pinhanez, Paulo Cavalin
This work explores the intrinsic limitations of the popular one-hot encoding method in classification of intents when detection of out-of-scope (OOS) inputs is required. Although r…
Towards a New Science of Disinformation
Claudio S. Pinhanez, German H. Flores, Marisa A. Vasconcelos +4
How can we best address the dangerous impact that deep learning-generated fake audios, photographs, and videos (a.k.a. deepfakes) may have in personal and societal life? We foresee…
Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms
Claudio Pinhanez, Paulo Cavalin, Victor Ribeiro +8
In this paper we explore the use of meta-knowledge embedded in intent identifiers to improve intent recognition in conversational systems. As evidenced by the analysis of thousands…
A Hybrid Solution to Learn Turn-Taking in Multi-Party Service-based Chat Groups
Maira Gatti de Bayser, Melina Alberio Guerra, Paulo Cavalin +1
To predict the next most likely participant to interact in a multi-party conversation is a difficult problem. In a text-based chat group, the only information available is the send…
Machine Teaching by Domain Experts: Towards More Humane,Inclusive, and Intelligent Machine Learning Systems
Claudio Pinhanez
This paper argues that a possible way to escape from the limitations of current machine learning (ML) systems is to allow their development directly by domain experts without the m…
Learning Multi-Party Turn-Taking Models from Dialogue Logs
Maira Gatti de Bayser, Paulo Cavalin, Claudio Pinhanez +1
This paper investigates the application of machine learning (ML) techniques to enable intelligent systems to learn multi-party turn-taking models from dialogue logs. The specific M…