Resources

• Framework to Assess the Robustness of Text Classification Systems - BODEGA framework

• Lexical Complexity Prediction and Simplification Dataset - MultiLS

• Lexical Simplification Dataset for English, Spanish and Portuguese - TSAR 2022

• Models and Synthetic Dataset for Fine-grained Emotion Classification - Emo Pillars

• Multilingual Easy-to-Read Translation Datasets and Evaluation Scripts - MER-TRANS

• Parlamentary British Sign Language and Catalan Sign Language Resources - BSL-Hansard and LSC-Hansard

• Sign Language Gloss Embedding Models

• Z-A parallel Catalan Sign Language video and Catalan time-aligned text dataset from parliamentary data. 

• Z-MER-TRANS Evaluation Scripts