91 citations · 177 across the 13 of their papers we have counts for
17 papers
Transformer-based segmentation of prosodic boundaries in Brazilian Portuguese
Rodrigo de Freitas Lima, Julio Cesar Galdino, Marcos Vinicius Treviso
Automatic prosodic segmentation identifies boundaries between speech units from acoustic and linguistic evidence. Although recent deep learning approaches have produced strong resu…
Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task
Ricardo Rei, Nuno M. Guerreiro, José Pombal +5
We present the joint contribution of Unbabel and Instituto Superior Técnico to the WMT 2023 Shared Task on Quality Estimation (QE). Our team participated on all tasks: sentence- an…
CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
Marcos Treviso, Alexis Ross, Nuno M. Guerreiro +1
Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, pr…
The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics
Ricardo Rei, Nuno M. Guerreiro, Marcos Treviso +3
Neural metrics for machine translation evaluation, such as COMET, exhibit significant improvements in their correlation with human judgments, as compared to traditional metrics bas…
CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task
Ricardo Rei, Marcos Treviso, Nuno M. Guerreiro +9
We present the joint contribution of IST and Unbabel to the WMT 2022 Shared Task on Quality Estimation (QE). Our team participated on all three subtasks: (i) Sentence and Word-leve…
Efficient Methods for Natural Language Processing: A Survey
Marcos Treviso, Ji-Ung Lee, Tianchu Ji +19
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance mea…
Learning to Scaffold: Optimizing Model Explanations for Teaching
Patrick Fernandes, Marcos Treviso, Danish Pruthi +2
Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal…
Predicting Attention Sparsity in Transformers
Marcos Treviso, António Góis, Patrick Fernandes +2
Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used b…
Sparse Continuous Distributions and Fenchel-Young Losses
André F. T. Martins, Marcos Treviso, António Farinhas +4
Exponential families are widely used in machine learning, including many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distr…
Sparse and Continuous Attention Mechanisms
André F. T. Martins, António Farinhas, Marcos Treviso +3
Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical di…
The Explanation Game: Towards Prediction Explainability through Sparse Communication
Marcos V. Treviso, André F. T. Martins
Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a laype…
Unbabel's Participation in the WMT19 Translation Quality Estimation Shared Task
Fabio Kepler, Jonay Trénous, Marcos Treviso +5
We present the contribution of the Unbabel team to the WMT 2019 Shared Task on Quality Estimation. We participated on the word, sentence, and document-level tracks, encompassing 3…
OpenKiwi: An Open Source Framework for Quality Estimation
Fábio Kepler, Jonay Trénous, Marcos Treviso +2
We introduce OpenKiwi, a PyTorch-based open source framework for translation quality estimation. OpenKiwi supports training and testing of word-level and sentence-level quality est…
Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks
Nathan Hartmann, Erick Fonseca, Christopher Shulby +3
Word embeddings have been found to provide meaningful representations for words in an efficient way; therefore, they have become common in Natural Language Processing sys- tems. In…
Evaluating Word Embeddings for Sentence Boundary Detection in Speech Transcripts
Marcos V. Treviso, Christopher D. Shulby, Sandra M. Aluisio
This paper is motivated by the automation of neuropsychological tests involving discourse analysis in the retellings of narratives by patients with potential cognitive impairment.…
PELESent: Cross-domain polarity classification using distant supervision
Edilson A. Corrêa, Vanessa Q. Marinho, Leandro B. dos Santos +3
The enormous amount of texts published daily by Internet users has fostered the development of methods to analyze this content in several natural language processing areas, such as…
Sentence Segmentation in Narrative Transcripts from Neuropsychological Tests using Recurrent Convolutional Neural Networks
Marcos Vinícius Treviso, Christopher Shulby, Sandra Maria Aluísio
Automated discourse analysis tools based on Natural Language Processing (NLP) aiming at the diagnosis of language-impairing dementias generally extract several textual metrics of n…