no code implementations • EAMT 2022 • Pedro Mota, Vera Cabarrão, Eduardo Farah
In this work, we propose a Named Entity handling approach to improve translation quality within an existing Natural Language Processing (NLP) pipeline without modifying the Neural Machine Translation (NMT) component.
no code implementations • EAMT 2022 • Miguel Menezes, Vera Cabarrão, Pedro Mota, None Helena Moniz, Alon Lavie
This paper describes the research developed at Unbabel, a Portuguese Machine-translation start-up, that combines MT with human post-edition and focuses strictly on customer service content.
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 • 13 Jun 2016 • Pedro Mota, Maxine Eskenazi, Luisa Coheur
In this context, we study how different weighting mechanisms influence the discovery of word communities that relate to the different topics found in the documents.