paper25.pdf - Deep Bidirectional Transformers for Italian Question Answering Danilo Croce and Giorgio Brandi and Roberto Basili Department Of Enterprise

paper25.pdf - Deep Bidirectional Transformers for Italian...

This preview shows page 1 - 2 out of 6 pages.

Deep Bidirectional Transformers for Italian Question Answering Danilo Croce and Giorgio Brandi and Roberto Basili Department Of Enterprise Engineering University of Roma, Tor Vergata Via del Politecnico 1, 00133 Roma { croce,basili } @info.uniroma2.it * Abstract English. 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. Re- cent works show that the application of Automatic Machine Translation is an en- abling 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 architec- ture, based on effective techniques re- cently proposed within the Bidirectional Encoder Representations from Transform- ers (BERT) paradigm. Italiano. I recenti studi sull’applicazione di metodi di Deep Learning hanno por- tato a risultati importanti rispetto a di- versi problemi di Natural Language Pro- cessing, come il Question Answering (QA) task. Sfortunatamente, i requisiti di tali sistemi di QA neurali sono molto strin- genti per quanto riguarda le dimensioni dei dataset necessari per addestrare i modelli pi´u complessi. Tuttavia, recenti lavori hanno dimostrato che ´e possibile applicare tecniche di traduzione automat- ica al fine di acquisire collezioni di es- empi di larga scala e addestrare architet- ture neurali per il Question Answering nelle lingue in cui i dati di training sono scarsi, come l’italiano. In questo la- voro, mostriamo come queste risorse per- mettono l’addestramento di una architet- tura neurale molto efficace, basata sul * “Copyright c 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).” paradigma noto come Bidirectional En- coder Representations from Transformers (BERT), con risultati che costituiscono lo stato dell’arte. 1 Introduction Question Answering (QA) ((Hirschman and Gaizauskas, 2001)) tackles the problem of return- ing one or more answers to a question posed by a user in natural language, using as source a large knowledge base or, even more often, a large scale text collection: in this setting, the answers corre- spond to sentences (or their fragments) stored in the text collection. A typical QA process consists of three main steps: the question processing that aims at extracting requirements and objectives of the user’s query, the retrieval phase where docu- ments and sentences that include the answers are retrieved from the text collection and the answer extraction phase that locates the answer within the candidate sentences (Harabagiu et al., 2000; Kwok et al., 2001).
Image of page 1
Image of page 2

You've reached the end of your free preview.

Want to read all 6 pages?

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Stuck? We have tutors online 24/7 who can help you get unstuck.
A+ icon
Ask Expert Tutors You can ask You can ask You can ask (will expire )
Answers in as fast as 15 minutes