Deep learning continues to achieve state-of-the-art results in several NLP tasks, such as Question Answering (QA). Unfortunately, the requirements of neural QA systems are very strict in the size of the involved training datasets. Recent works show that the application of Automatic Machine Translation is an enabling factor for the acquisition of large scale QA training sets in resource poor languages such as Italian. In this work, we show how these resources can be used to train a state-of-the-art deep architecture, based on effective techniques recently proposed within the Bidirectional Encoder Representations from Transformers (BERT) paradigm.
Croce, D., Brandi, G., Basili, R. (2019). Deep bidirectional transformers for Italian question answering. In CEUR Workshop Proceedings. CEUR-WS.
Deep bidirectional transformers for Italian question answering
Croce D.;Basili R.
2019-11-13
Abstract
Deep learning continues to achieve state-of-the-art results in several NLP tasks, such as Question Answering (QA). Unfortunately, the requirements of neural QA systems are very strict in the size of the involved training datasets. Recent works show that the application of Automatic Machine Translation is an enabling factor for the acquisition of large scale QA training sets in resource poor languages such as Italian. In this work, we show how these resources can be used to train a state-of-the-art deep architecture, based on effective techniques recently proposed within the Bidirectional Encoder Representations from Transformers (BERT) paradigm.File | Dimensione | Formato | |
---|---|---|---|
clic2019.pdf
solo utenti autorizzati
Licenza:
Copyright dell'editore
Dimensione
522.79 kB
Formato
Adobe PDF
|
522.79 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.