Large-Scale Text Understanding Systems Lab (LaSTUS) @ TALN - Universitat Pompeu Fabra (UPF)

TSAR-2022-Shared-Task

TSAR2022 Shared Task on Lexical Simplification - Datasets and Evaluation scripts

Syntax-Aware-Transformer-Text2Gloss

This repository contains the code of the experiments reported in the paper "Syntax-aware Transformers for Neural Machine Translation: The Case ofText to Sign Gloss Translation". This paper was accepted for the Workshop BUCC2021 in the conference RANLP 2021.

SciARG

Corpus and code for argument mining in scientific abstracts in two scientific disciplines. Experiments with BERT-based models and domain adaptation from computational linguistics to biomedicine.

TSAR-LSBert

An adaptation of the LSBert system (Qiang et al., 2021) used as a baseline for the TSAR 2022 Shared Task Evaluation.

ALEXSIS

ALEXSIS: A Dataset for Benchmarking Lexical Simplification for Spanish

AsisTerm

Asistente para la anotación y expansión de definiciones de conceptos médicos en español

BSL-Hansard-tools

IroMovies

Dataset of Movie Reviews Annotated for Irony

NMT-Evaluation

signON_elan_processing