José G. C. de Souza

27 papers · 2014–2024 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) 🏃 Academic Marathon (10) 🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (5) 🗺️ Taxonomy Completionist (44) 🏆 Keyword Champion (4) 🔬 Deep Specialist (17) 🤝 Dynamic Duo (13) 💎 Century Club (27) 🗃️ Keyword Collector (82) ⚡ Prolific Year (7) ❓ The Questioner

Conferences

EMNLP (15) ACL (4) NAACL (3) COLING (2) IJCNLP (1) NIPS (1) SEMEVAL (1)

Top co-authors

Ricardo Rei (13) Marco Turchi (10) André F. T. Martins (10) Matteo Negri (10) Nuno M. Guerreiro (6) Ana C Farinha (6) Chrysoula Zerva (6) Andre Martins (5) Duarte Alves (5) António Farinhas (5)

Keywords

machine translation (15) quality estimation (10) neural machine translation (5) multidimensional quality metrics (4) large language model (4) sentence-level prediction (4) word-level prediction (4) multilingual model (3) chat translation (3) quality-aware decoding (3) direct assessment (3) text generation (2) bilingual conversation (2) translation quality (2) beam search (2) machine translation evaluation (2) minimum bayes risk (2) preference learning (1) multilingual translation (1) metropolis-hastings sampling (1)

Papers

Findings of the WMT 2024 Shared Task on Chat Translation EMNLP 2024

Findings of the Quality Estimation Shared Task at WMT 2024: Are LLMs Closing the Gap in QE? EMNLP 2024

Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation EMNLP 2024

QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation NIPS 2024

Tower v2: Unbabel-IST 2024 Submission for the General MT Shared Task EMNLP 2024

An Empirical Study of Translation Hypothesis Ensembling with Large Language Models EMNLP 2023

Findings of the WMT 2023 Shared Task on Quality Estimation EMNLP 2023

Scaling up CometKiwi: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task EMNLP 2023

Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning EMNLP 2023

Unbabel-IST at the WMT Chat Translation Shared Task EMNLP 2022

Findings of the WMT 2022 Shared Task on Quality Estimation EMNLP 2022

Robust MT Evaluation with Sentence-level Multilingual Augmentation EMNLP 2022

COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task EMNLP 2022

CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task EMNLP 2022

Findings of the WMT 2022 Shared Task on Chat Translation EMNLP 2022

Quality-Aware Decoding for Neural Machine Translation NAACL 2022

IST-Unbabel 2021 Submission for the Quality Estimation Shared Task EMNLP 2021

Quality Estimation for Automatically Generated Titles of eCommerce Browse Pages NAACL 2018

TMop: a Tool for Unsupervised Translation Memory Cleaning ACL 2016

TranscRater: a Tool for Automatic Speech Recognition Quality Estimation ACL 2016

FBK HLT-MT at SemEval-2016 Task 1: Cross-lingual Semantic Similarity Measurement Using Quality Estimation Features and Compositional Bilingual Word Embeddings SEMEVAL 2016

Multitask Learning for Adaptive Quality Estimation of Automatically Transcribed Utterances NAACL 2015

Online Multitask Learning for Machine Translation Quality Estimation ACL 2015

Online Multitask Learning for Machine Translation Quality Estimation IJCNLP 2015

Adaptive Quality Estimation for Machine Translation ACL 2014

Machine Translation Quality Estimation Across Domains COLING 2014

Quality Estimation for Automatic Speech Recognition COLING 2014