Building the state-of-the-art in POS tagging of Italian Tweets
In this paper we describe our approach to EVALITA 2016 POS tagging for Italian Social Media Texts (PoSTWITA). We developed a two-branch bidirectional Long Short Term Memory recurrent neural network, where the first bi-LSTM uses a typical vector representation for the input words, while the second on...
Sparad:
| Huvudupphov: | , |
|---|---|
| Materialtyp: | Chapter |
| Språk: | Inglês |
| Utgiven: |
Accademia University Press
2016
|
| Länkar: | https://doi.org/10.4000/books.aaccademia.1959 https://hdl.handle.net/20.500.13089/1d4p https://books.openedition.org/aaccademia/1959 |
| Taggar: |
Inga taggar, Lägg till första taggen!
|