About m.nissim

This author has not yet filled in any details.
So far m.nissim has created 3 blog entries.

COVID-19 Browser: Using Natural Language Processing to Fight the Pandemic

Our society is facing an unprecedented crisis due to the recent COVID-19 outbreak that is putting sanitary systems in check all around the world. Recently, dozens of countries announced the shutdown of all non-essential activities for the next foreseeable future, and scientists are striving worldwide to find cures and vaccines able to stop the ongoing pandemic.

In these hard times, everyone should put their expertise at play to help in the fight against the virus. For Gabriele Sarti, a Data Science student at the University of Trieste and a young member of the Italian Association for Computational Linguistics (AILC), this meant exploiting his expertise in Natural Language Processing (NLP) to develop the COVID-19 Browser, a system leveraging state-of-the-art techniques in NLP to extract meaningful information and guide scientists towards a better understanding of COVID-19.

As of today, more than 32 000 scientific papers have been published by research laboratories worldwide on the topics of the new corona virus SARS-CoV-2 and the disease COVID-19. It is very likely that in such a large quantity of text a lot of useful information is lost, making our knowledge on the subject too sparse to be exploited to its full potential. COVID-19 Browser allows users to browse a large collection of those articles directly in their console, matching article’s abstracts with user queries formulated in natural language to delve deeper in our current knowledge of the subject.

The model underlying Covid-19 Browser is SciBERT-NLI, a cutting-edge language model trained by the American nonprofit AI2 on a corpus of 1.14M scientific papers and subsequently adjusted by Gabriele to be used for the retrieval task.

Gabriele Sarti is a student in the Data Science master at the University of Trieste (https://dssc.units.it/), and is affiliated with SISSA (https://www.sissa.it), and the CNR ItaliaNLP Lab in Pisa (http://www.italianlp.it). He is a member of the Italian Association for Computational Linguistics (https://www.ai-lc.it/en/) and plays an active role in its Dissemination Team.

Links

By |2020-04-06T10:33:03+02:0024 Mar, 2020|BLOG, RESEARCH|

AILC Master Thesis Prize 2017 assigned

This year, in connection with its annual conference (CLiC-it), for the first time AILC introduced a prize for the best master thesis in computational linguistics defended at an Italian University.

The committee was composed by a member of the AILC board (Felice Dell’Orletta), a chair of CLiC-it 2016 (Anna Corazza), and a chair of CLiC-it 2017 (Malvina Nissim). Theses defended between January 1st 2016 and July 31st 2017 were eligible for the 2017 edition.

Ten theses were submitted, with the following geographical distribution: Pisa (4),Turin (3), Parma (1),  Siena (1), Trento (1). Gender was balanced, with five theses written by female students and five by male students.

The evaluation was performed by the three committee members individually in a first stage, after having agreed on a set of specific criteria which had to do both with content (including originality and timeliness of the topic), as well as writing (including clarity, style, and the structure of the thesis). At a second stage, the committee jointly discussed each thesis in details during several Skype meetings, and came up with a short list of three theses, which all deserved the prize. The choice of a final winner was not at all easy, and the reason why eventually we selected the one we selected is its being the closest to the core of our discipline. The first AILC prize for the best master thesis in computational linguistics was thus awarded to:

Alessio Miaschi, Università di Pisa: “Definizione di modelli computazionali per lo studio dell’evoluzione delle abilità di scrittura a partire da un corpus di produzioni scritte di apprendenti della scuola secondaria di primo grado

This is a work that involves both the development of a working system that models a specific language phenomenon, as well as a thorough linguistic analysis based on the features used and on detailed error analysis. All this on top of an excellent background overview, and a view to concrete, future applications, directly useful to society.

The other two theses which made it to the final selection were the following:

Chiara Alzetta, Università di Pisa: “Studio linguistico-computazionale per l’analisi dei tipi linguistici. Similarità e differenze nel confronto fra Universal Dependencies Treebanks”

Enrico Mensa, Università di Torino: “Design and implementation of a methodology for the alignment of semantic resources and the automatic population of Conceptual Spaces”

As part of the prize, Alessio received a monetary sum from AILC, free membership to the association for one year, and free attendance to CLiC-it 2017. At the conference the whole community got the chance to listen to Alessio’s presentation of his thesis, right at the end of a panel specifically dedicated to the teaching of computational linguistics and Natural Language Processing in Italy. This was a nice fit, since the high quality of the submitted works really goes to show how much talent, both among students and among teachers there is at Italian institutions in the field of computational linguistics.

We are already looking forward to next edition!

Anna Corazza, Felice Dell’Orletta, and Malvina Nissim

By |2019-01-27T17:44:01+01:0020 Dec, 2017|EDUCATION, NEWS|
Go to Top