???global.info.a_carregar???
Identification

Personal identification

Full name
Marcos Vinicius Treviso

Citation names

  • Treviso, M. V.

Author identifiers

Ciência ID
7716-A2C9-3CCA
ORCID iD
0000-0002-3286-0609

Knowledge fields

  • Engineering and Technology - Electrotechnical Engineering, Electronics and Informatics - Electrical and Electronic Engineering

Languages

Language Speaking Reading Writing Listening Peer-review
Portuguese (Mother tongue)
English Advanced (C1) Advanced (C1) Advanced (C1) Advanced (C1) Advanced (C1)
Education
Degree Classification
2019 - 2023
Ongoing
 Engenharia Eletrotécnica e de Computadores (Doutoramento)
Universidade de Lisboa Instituto Superior Técnico, Portugal
2016 - 2018
Concluded
 Ciência da Computação e Matemática Computacional (Master)
Universidade de São Paulo Câmpus de São Carlos, Brazil
2012 - 2015
Concluded
 Ciência da Computação (Bachelor)
Universidade Federal do Pampa, Brazil
Outputs

Publications

Conference paper
  1. Treviso, M. V.; Góis, António; Fernandes, Patrick; Fonseca, Erick; AF Martins. "Predicting Attention Sparsity in Transformers". 2021.
    10.48550/ARXIV.2109.12188
  2. Treviso, Marcos; Guerreiro, Nuno; Rei, Ricardo; AF Martins. Corresponding author: Treviso, Marcos. "IST-Unbabel 2021 Submission for the Explainable Quality Estimation Shared Task". 2021.
    10.18653/v1/2021.eval4nlp-1.14
  3. Treviso, Marcos; Martins, André F. T.. "The Explanation Game: Towards Prediction Explainability through Sparse Communication". 2020.
    10.18653/v1/2020.blackboxnlp-1.10
  4. Casanova, Edresson; Treviso, Marcos; Hübner, Lilian; Aluísio, Sandra. "Evaluating Sentence Segmentation in Different Datasets of Neuropsychological Language Tests in Brazilian Portuguese". 2020.
  5. Martins, André F. T.; Farinhas, António; Treviso, Marcos; Niculae, Vlad; Aguiar, Pedro; Figueiredo, Mário. "Sparse and Continuous Attention Mechanisms". 2020.
  6. Kepler, Fabio; Trénous, Jonay; Treviso, Marcos; Vera, Miguel; Góis, António; Farajian, M. Amin; Lopes, António V.; Martins, André F. T.. "Unbabel's Participation in the WMT19 Translation Quality Estimation Shared Task". 2019.
    10.18653/v1/w19-5406
  7. Kepler, Fabio; Trénous, Jonay; Treviso, Marcos; Vera, Miguel; Martins, André F. T.. "OpenKiwi: An Open Source Framework for Quality Estimation". 2019.
    10.18653/v1/p19-3020
  8. Treviso, Marcos; Aluísio, Sandra. "Sentence Segmentation and Disfluency Detection in Narrative Transcripts from Neuropsychological Tests". 2018.
  9. Treviso, Marcos; Shulby, Christopher; Aluísio, Sandra. "Evaluating Word Embeddings for Sentence Boundary Detection in Speech Transcripts". Paper presented in Brazilian Symposium in Information and Human Language Technology, Uberlândia, 2017.
  10. Hartmann, Nathan; Fonseca, Erick; Shulby, Christopher; Treviso, Marcos; Silva, Jéssica; Aluísio, Sandra. "Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks". Paper presented in Brazilian Symposium in Information and Human Language Technology, Uberlândia, 2017.
  11. Treviso, Marcos; Shulby, Christopher; Aluísio, Sandra. "Sentence Segmentation in Narrative Transcripts from Neuropsychological Tests using Recurrent Convolutional Neural Networks". Paper presented in Conference of the European Chapter of the Association for Computational Linguistics, Valencia, 2017.
  12. Corrêa Jr., Edilson; Marinho, Vanessa; Dos Santos, Leandro; Bertaglia, Thales; Treviso, Marcos; Brum, Henrico. "PELESent: Cross-domain polarity classification using distant supervision". Paper presented in 2017 Brazilian Conference on Intelligent Systems, Uberlândia, 2017.
Journal article
  1. AF Martins; Treviso, M. V.; Farinhas, António; Aguiar, Pedro; Figueiredo, Mário; Blondel, Mathieu; Niculae, Vlad. "Sparse Continuous Distributions and Fenchel-Young Losses". Journal of Machine Learning (JMLR) (2021): https://arxiv.org/abs/2108.01988.
    10.48550/ARXIV.2108.01988
  2. Treviso, Marcos Vinícius; Dos Santos, Leandro Borges; Shulby, Christopher; Hübner, Lilian Cristine; Mansur, Letícia Lessa; Aluísio, Sandra Maria. "Detecting mild cognitive impairment in narratives in Brazilian Portuguese: first steps towards a fully automated system". Letras de Hoje 53 1 (2018): 48. http://dx.doi.org/10.15448/1984-7726.2018.1.30955.
    10.15448/1984-7726.2018.1.30955
Thesis / Dissertation
  1. Treviso, Marcos Vinícius. "Segmentação de sentenças e detecção de disfluências em narrativas transcritas de testes neuropsicológicos". Master, Universidade de São Paulo, 2018. http://dx.doi.org/10.11606/d.55.2018.tde-05022018-090740.
    10.11606/d.55.2018.tde-05022018-090740
Distinctions

Award

2019 Best Demo Paper Award at ACL
2018 Best Dissertation on Language Technology for Portuguese (from 2015 to 2018)
Conferência Internacional de Processamento Computacional da Língua Portuguesa, Brazil