no code implementations • EMNLP 2020 • Paulo Cavalin, Victor Henrique Alves Ribeiro, Ana Appel, Claudio Pinhanez
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.
no code implementations • 18 May 2022 • 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.
no code implementations • ACL 2021 • Claudio Pinhanez, Paulo Cavalin, Victor Henrique Alves Ribeiro, Ana Appel, Heloisa Candello, Julio Nogima, Mauro Pichiliani, Melina Guerra, Maira de Bayser, Gabriel Malfatti, Henrique Ferreira
In this paper we explore the improvement of intent recognition in conversational systems by the use of meta-knowledge embedded in intent identifiers.
no code implementations • 16 Dec 2020 • Claudio Pinhanez, Paulo Cavalin, Victor Ribeiro, Heloisa Candello, Julio Nogima, Ana Appel, Mauro Pichiliani, Maira Gatti de Bayser, Melina Guerra, Henrique Ferreira, Gabriel Malfatti
By using neuro-symbolic algorithms able to incorporate such proto-taxonomies to expand intent representation, we show that such mined meta-knowledge can improve accuracy in intent recognition.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Paulo Cavalin, Marisa Vasconcelos, Marcelo Grave, Claudio Pinhanez, Victor Henrique Alves Ribeiro
We present a method for creating parallel data to train Seq2Seq neural networks for sentiment transfer.
no code implementations • 14 Jan 2020 • Maira Gatti de Bayser, Melina Alberio Guerra, Paulo Cavalin, Claudio Pinhanez
To predict the next most likely participant to interact in a multi-party conversation is a difficult problem.
no code implementations • 3 Jul 2019 • Maira Gatti de Bayser, Paulo Cavalin, Claudio Pinhanez, Bianca Zadrozny
This paper investigates the application of machine learning (ML) techniques to enable intelligent systems to learn multi-party turn-taking models from dialogue logs.
no code implementations • 24 Aug 2018 • Claudio S. Pinhanez, Heloisa Candello, Mauro C. Pichiliani, Marisa Vasconcelos, Melina Guerra, Maíra G. de Bayser, Paulo Cavalin
This work compares user collaboration with conversational personal assistants vs. teams of expert chatbots.
no code implementations • 3 May 2017 • Maira Gatti de Bayser, Paulo Cavalin, Renan Souza, Alan Braz, Heloisa Candello, Claudio Pinhanez, Jean-Pierre Briot
Multi-party Conversational Systems are systems with natural language interaction between one or more people or systems.