Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling
Pierpaolo Basile, Giovanni Maria Semeraro, Pierluigi Cassotti · Accademia University Press eBooks · 2017
In this paper, we propose a Deep Learning architecture for sequence labeling based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. We evaluate the proposed method on three Natural Language Processing tasks for Italian: PoS-tagging of tweets, Named Entity Recognition and Super-Sense Tagging. Results show that the system is able to achieve state of the art performance in all the tasks and in some cases overcomes the best systems previously developed for the Italian.