Exploiting Qualitative Information from Automatic Word Alignment for Cross-lingual NLP Tasks

no code implementations • ACL 2013 • Jos{\'e} G. C. de Souza, Miquel Espl{\`a}-Gomis, Marco Turchi, Matteo Negri

Machine Translation Natural Language Inference +2

Adaptive Quality Estimation for Machine Translation

no code implementations • ACL 2014 • Marco Turchi, Antonios Anastasopoulos, Jos{\'e} G. C. de Souza, Matteo Negri

Machine Translation Translation

Machine Translation Quality Estimation Across Domains

no code implementations • COLING 2014 • Jos{\'e} G. C. de Souza, Marco Turchi, Matteo Negri

Machine Translation Translation

Quality Estimation for Automatic Speech Recognition

no code implementations • COLING 2014 • Matteo Negri, Marco Turchi, Jos{\'e} G. C. de Souza, Daniele Falavigna

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Online Multitask Learning for Machine Translation Quality Estimation

1 code implementation • IJCNLP 2015 • Jos{\'e} G. C. de Souza, Matteo Negri, Elisa Ricci, Marco Turchi

Machine Translation Translation

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

no code implementations • SEMEVAL 2016 • Duygu Ataman, Jos{\'e} G. C. de Souza, Marco Turchi, Matteo Negri

Cross-Lingual Semantic Textual Similarity Machine Translation +6

The FBK Participation in the WMT 2016 Automatic Post-editing Shared Task

no code implementations • WS 2016 • Rajen Chatterjee, Jos{\'e} G. C. de Souza, Matteo Negri, Marco Turchi

Automatic Post-Editing Data Augmentation

TMop: a Tool for Unsupervised Translation Memory Cleaning

1 code implementation • ACL 2016 • Masoud Jalili Sabet, Matteo Negri, Marco Turchi, Jos{\'e} G. C. de Souza, Marcello Federico

Machine Translation Translation

Quality Estimation for Automatically Generated Titles of eCommerce Browse Pages

no code implementations • NAACL 2018 • Nicola Ueffing, Jos{\'e} G. C. de Souza, Gregor Leusch

In this paper, we present different approaches: The first one is a Random Forest (RF) model that explores hand-crafted, robust features, which are a mix of established features commonly used in Machine Translation Quality Estimation (MTQE) and new features developed specifically for our task.

Machine Translation Translation