publications

An up-to-date list is available on Google Scholar.
* denotes equal contribution.

Papers

2023

  1. ACL
    CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
    Marcos Treviso, Alexis Ross, Nuno M. Guerreiro, and André Martins
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023
  2. ACL
    The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics
    Ricardo Rei, Nuno M. Guerreiro, Marcos Treviso, Luisa Coheur, Alon Lavie, and André Martins
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Jul 2023
  3. TACL
    Efficient Methods for Natural Language Processing: A Survey
    Marcos Treviso*, Ji-Ung Lee*, Tianchu Ji*, Betty van Aken, Qingqing Cao, Manuel R. Ciosici, Michael Hassid, Kenneth Heafield, Sara Hooker, Colin Raffel, Pedro H. Martins, André F. T. Martins, Jessica Zosa Forde, Peter Milder, Edwin Simpson, Noam Slonim, Jesse Dodge, Emma Strubell, Niranjan Balasubramanian, Leon Derczynski, Iryna Gurevych, and Roy Schwartz
    Transactions of the Association for Computational Linguistics, Jul 2023

2022

  1. WMT ★ Shared Task
    Winner Award
    CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task
    Ricardo Rei*, Marcos Treviso*, Nuno M. Guerreiro*, Chrysoula Zerva*, Ana C Farinha, Christine Maroti, José G. Souza, Taisiya Glushkova, Duarte Alves, Luisa Coheur, Alon Lavie, and André F. T. Martins
    In Proceedings of the Seventh Conference on Machine Translation (WMT), Dec 2022
  2. NeurIPS
    Learning to Scaffold: Optimizing Model Explanations for Teaching
    Patrick Fernandes*, Marcos Treviso*, Danish Pruthi, Andre Martins, and Graham Neubig
    In Thirty-Sixth Conference on Neural Information Processing Systems, Dec 2022
  3. SPNLP
    Predicting Attention Sparsity in Transformers
    Marcos Treviso, António Góis, Patrick Fernandes, Erick Fonseca, and Andre Martins
    In Proceedings of the Sixth Workshop on Structured Prediction for NLP, May 2022
  4. JMLR
    Sparse continuous distributions and Fenchel-Young losses
    André FT Martins, Marcos Treviso, António Farinhas, Pedro MQ Aguiar, Mário AT Figueiredo, Mathieu Blondel, and Vlad Niculae
    Journal of Machine Learning Research, May 2022

2021

  1. Eval4NLP ★ Best Explain.
    Approach Award
    IST-Unbabel 2021 Submission for the Explainable Quality Estimation Shared Task
    Marcos Treviso, Nuno Guerreiro, Ricardo Rei, and André F. T. Martins
    In Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems, Nov 2021

2020

  1. BlackboxNLP
    The Explanation Game: Towards Prediction Explainability through Sparse Communication
    Marcos Treviso, and André F. T. Martins
    In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, Nov 2020
  2. NeurIPS ★ Spotlight
    Presentation
    Sparse and Continuous Attention Mechanisms
    André Martins, António Farinhas, Marcos Treviso, Vlad Niculae, Pedro Aguiar, and Mario Figueiredo
    In Advances in Neural Information Processing Systems, Nov 2020
  3. LREC
    Evaluating Sentence Segmentation in Different Datasets of Neuropsychological Language Tests in Brazilian Portuguese
    Edresson Casanova, Marcos Treviso, Lilian Hübner, and Sandra Aluı́sio
    In Proceedings of the 12th Language Resources and Evaluation Conference, May 2020

2019

  1. ACL ★ Best Demo
    Paper Award
    OpenKiwi: An Open Source Framework for Quality Estimation
    Fabio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera, and André F. T. Martins
    In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Jul 2019
  2. WMT-QE ★ Shared Task
    Winner Award
    Unbabel’s Participation in the WMT19 Translation Quality Estimation Shared Task
    Fabio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera, António Góis, M. Amin Farajian, António V. Lopes, and André F. T. Martins
    In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), Aug 2019

2018

  1. PROPOR ★ Best MSc
    Thesis Award
    Sentence Segmentation and Disfluency Detection in Narrative Transcripts from Neuropsychological Tests
    Marcos Treviso, and Sandra Maria Aluísio
    In Computational Processing of the Portuguese Language, Aug 2018
  2. Detecting mild cognitive impairment in narratives in Brazilian Portuguese: first steps towards a fully automated system
    Marcos Treviso, Leandro Borges Santos, Christopher Shulby, Lilian Cristine Hübner, Letícia Lessa Mansur, and Sandra Maria Aluísio
    Letras de Hoje, Jun 2018

2017

  1. EACL
    Sentence Segmentation in Narrative Transcripts from Neuropsychological Tests using Recurrent Convolutional Neural Networks
    Marcos Treviso, Christopher Shulby, and Sandra Aluı́sio
    In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, Apr 2017
  2. STIL
    Evaluating Word Embeddings for Sentence Boundary Detection in Speech Transcripts
    Marcos Treviso, Christopher Shulby, and Sandra Aluı́sio
    In Proceedings of the 11th Brazilian Symposium in Information and Human Language Technology, Oct 2017
  3. STIL
    Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks
    Nathan Hartmann, Erick Fonseca, Christopher Shulby, Marcos Treviso, Jéssica Silva, and Sandra Aluı́sio
    In Proceedings of the 11th Brazilian Symposium in Information and Human Language Technology, Oct 2017
  4. BRACIS
    PELESent: Cross-domain polarity classification using distant supervision
    Edilson Anselmo Corrêa, Vanessa Queiroz Marinho, Leandro Borges Santos, Thales F. C. Bertaglia, Marcos Treviso, and Henrico Bertini Brum
    In 2017 Brazilian Conference on Intelligent Systems (BRACIS), Oct 2017

Theses

  1. Ph.D.
    Selective Sparsity for Explainability with Applications to Translation Quality Estimation
    Marcos Vinicius Treviso
    Instituto Superior Técnico, 2023
  2. M.Sc.
    Segmentação de sentenças e detecção de disfluências em narrativas transcritas de testes neuropsicológicos
    Marcos Vinicius Treviso
    Universidade de São Paulo, 2017
  3. B.Sc.
    Dois modelos de aprendizagem profunda para análise morfossintática
    Marcos Vinicius Treviso
    Universidade Federal do Pampa, 2015