Integrating Machine Learning Data with Symbolic Knowledge from Collaboration Practices of Curators to Improve Conversational Systems
- 2021
- CHI 2021
Paulo Cavalin
Title
Research Scientist
Bio
Paulo Cavalin is a Research Scientist of the Conversational Intelligence Group, at IBM Research - Brazil, conducting both theoretical and applied research in Machine Learning, with particular focus on Natural Language Processing problems such as text classification and machine translation for conversational systems. Currently he is working with Foundation Models, focusing on understand their applicability for endangered, very-low-resource, languages such as Brazilian Indigenous Languages.
He holds a Ph.D. degree in Automated Production Engineering/Computer Science from École de Technologie Supérieure (ETS) - Université du Québec, Montreal (QC) - Canada, obtained in 2011, and 15+ years of experience in research in AI-related areas such as Machine Learning, Pattern Recognition, Computer Vision, and Social Data Analytics.
He is also an author of dozens of peer-reviewed scientific papers and an inventor of several patents. A detailed list of can be found at Google Scholar profile.
Publications
Improving out-of-scope detection in intent classification by using embeddings of the word graph space of the classes
- Paulo Cavalin
- Victor Henrique Alves Ribeiro
- et al.
- 2020
- EMNLP 2020
From disjoint sets to parallel data to train seq2seq models for sentiment transfer
- Paulo Cavalin
- Marisa Vasconcelos
- et al.
- 2020
- EMNLP 2020
Intentions, Meanings, and Whys: Designing Content for Voice-based Conversational Museum Guides
- Fabricio Barth
- Heloisa Candello
- et al.
- 2020
- CUI 2020
Creating Corpora for Seq2Seq Tone Rephrasing Using Social Media Posts
- Paulo Cavalin
- Marisa Vasconcelos
- et al.
- 2020
- IJCNN 2020
Dynamic Multi-criteria Classifier Selection for Illegal Tapping Detection in Oil Pipelines
- Victor Henrique Alves Ribeiro
- Pedro Henrique Domingues
- et al.
- 2020
- IJCNN 2020
Live It Up: Analyzing emotions and language use in tweets during the soccerworld cup finals
- Marisa Vasconcelos
- Jussara M. Almeida
- et al.
- 2019
- WebSci 2019
Ore content estimation based on spatial geological data through 3D convolutional neural networks
- B. W.Carvalho Wsr
- Daniel Civitarese
- et al.
- 2019
- EAGE Workshop 2019
The effect of audiences on the user experience with conversational interfaces in physical spaces
- 2019
- CHI 2019
Towards a human-in-the-loop library for tracking hyperparameter tuning in deep learning development
- Renan Souza
- Liliane Neves
- et al.
- 2018
- LADaS 2018
Patents
- US
- 12159238
- TW
- I814394
- US
- 11677692
- US
- 11562028
- CN
- ZL201880049711.4
- US
- 11238100
- US
- 11216768
- JP
- 7002633
- US
- 11194966
- US
- 10990882
Projects
Conversational Intelligence
Exploring AI-based conversational systems in a human-centered approach
Top collaborators
CS
Claudio Santos Pinhanez
Principal Research Scientist, Conversational Intelligence, STSM
Hd
Heloisa Candello
Senior Research Scientist