no code implementations • LREC 2020 • Pedro Cabral, Matilde Gon{\c{c}}alves, Hugo Nicolau, Lu{\'\i}sa Coheur, Ruben Santos
Here, we present PE2LGP, an authoring system that features a 3D avatar that signs Portuguese Sign Language.
no code implementations • LREC 2020 • Carolina Neves, Lu{\'\i}sa Coheur, Hugo Nicolau
Avatars that can animate sign languages have gained an increase of interest in this area due to their flexibility in the process of generation and edition.
no code implementations • CONLL 2019 • Pedro Mota, Maxine Eskenazi, Lu{\'\i}sa Coheur
We propose BeamSeg, a joint model for segmentation and topic identification of documents from the same domain.
no code implementations • SEMEVAL 2019 • Eug{\'e}nio Ribeiro, V{\^a}nia Mendon{\c{c}}a, Ricardo Ribeiro, David Martins de Matos, Alberto Sardinha, Ana L{\'u}cia Santos, Lu{\'\i}sa Coheur
We approach all the subtasks by applying a graph clustering algorithm on contextualized embedding representations of the verbs and arguments.
no code implementations • SEMEVAL 2017 • Pedro Fialho, Hugo Patinho Rodrigues, Lu{\'\i}sa Coheur, Paulo Quaresma
This paper describes our approach to the SemEval-2017 {``}Semantic Textual Similarity{''} and {``}Multilingual Word Similarity{''} tasks.
no code implementations • LREC 2016 • {\^A}ngela Costa, Rui Correia, Lu{\'\i}sa Coheur
In this paper we describe a corpus of automatic translations annotated with both error type and quality.
no code implementations • LREC 2014 • Angela Costa, Tiago Lu{\'\i}s, Lu{\'\i}sa Coheur
Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved.
no code implementations • LREC 2014 • S{\'e}rgio Curto, Ana C. Mendes, Pedro Curto, Lu{\'\i}sa Coheur, {\^A}ngela Costa
We present JUST. ASK, a publicly available Question Answering system, which is freely available.
no code implementations • LREC 2012 • Jo{\~a}o Silva, Lu{\'\i}sa Coheur, {\^A}ngela Costa, Isabel Trancoso
In Statistical Machine Translation, words that were not seen during training are unknown words, that is, words that the system will not know how to translate.
no code implementations • LREC 2012 • {\^A}ngela Costa, Tiago Lu{\'\i}s, Joana Ribeiro, Ana Cristina Mendes, Lu{\'\i}sa Coheur
Finally, we present a taxonomy of translation errors, according to which we analyze the output of the automatic translation before and after using the corpus as training data.
no code implementations • LREC 2012 • Pedro Fialho, S{\'e}rgio Curto, Ana Cristina Mendes, Lu{\'\i}sa Coheur
The WordNet knowledge model is currently implemented in multiple software frameworks providing procedural access to language instances of it.