no code implementations • FEVER (ACL) 2022 • Marco Mori, Paolo Papotti, Luigi Bellomarini, Oliver Giudice
Computational fact-checking aims at supporting the verification process of textual claims by exploiting trustworthy sources.
no code implementations • INLG (ACL) 2021 • Rayhane Rezgui, Mohammed Saeed, Paolo Papotti
We present a generic method to compute thefactual accuracy of a generated data summarywith minimal user effort.
no code implementations • EMNLP (FEVER) 2021 • Mohammed Saeed, Giulio Alfarano, Khai Nguyen, Duc Pham, Raphael Troncy, Paolo Papotti
Computational fact-checking has gained a lot of traction in the machine learning and natural language processing communities.
1 code implementation • 9 Feb 2024 • Riccardo Cappuzzo, Gael Varoquaux, Aimee Coelho, Paolo Papotti
We present an in-depth analysis of data discovery in data lakes, focusing on table augmentation for given machine learning tasks.
no code implementations • 2 Nov 2023 • Kensuke Mitsuzawa, Motonobu Kanagawa, Stefano Bortoli, Margherita Grossi, Paolo Papotti
For this optimisation, we introduce sparse regularisation and propose two methods for dealing with the issue of selecting an appropriate regularisation parameter.
no code implementations • 2 Apr 2023 • Mohammed Saeed, Nicola De Cao, Paolo Papotti
Thus, we envision the use of SQL queries to cover a broad range of data that is not captured by traditional databases by tapping the information in LLMs.
1 code implementation • 19 Aug 2022 • Mohammed Saeed, Nicolas Traub, Maelle Nicolas, Gianluca Demartini, Paolo Papotti
Fact-checking is one of the effective solutions in fighting online misinformation.
1 code implementation • 16 Dec 2021 • Naser Ahmadi, Hansjorg Sand, Paolo Papotti
Our method builds a fine-grained graph over the content of the corpora and derives word embeddings to represent the objects to match in a low dimensional space.
1 code implementation • EMNLP 2021 • Mohammed Saeed, Naser Ahmadi, Preslav Nakov, Paolo Papotti
While pre-trained language models (PLMs) are the go-to solution to tackle many natural language processing problems, they are still very limited in their ability to capture and to use common-sense knowledge.
no code implementations • 13 Mar 2021 • Preslav Nakov, David Corney, Maram Hasanain, Firoj Alam, Tamer Elsayed, Alberto Barrón-Cedeño, Paolo Papotti, Shaden Shaar, Giovanni Da San Martino
The reporting and the analysis of current events around the globe has expanded from professional, editor-lead journalism all the way to citizen journalism.
no code implementations • 15 Nov 2019 • Graziano Mita, Paolo Papotti, Maurizio Filippone, Pietro Michiardi
We present a novel method - LIBRE - to learn an interpretable classifier, which materializes as a set of Boolean rules.
no code implementations • 3 Sep 2019 • Riccardo Cappuzzo, Paolo Papotti, Saravanan Thirumuruganathan
The embeddings are learned based on such sentences.
no code implementations • 21 Jun 2019 • Naser Ahmadi, Joohyung Lee, Paolo Papotti, Mohammed Saeed
One challenge in fact checking is the ability to improve the transparency of the decision.
1 code implementation • ICDE 2018 • Stefano Ortona, Venkata Vamsikrishna Meduri, Paolo Papotti
We present RUDIK, a system for the discovery of declarative rules over knowledge-bases (KBs).
1 code implementation • 23 Dec 2017 • Fnu Suya, Yuan Tian, David Evans, Paolo Papotti
Specifically, we consider the problem of attacking machine learning classifiers subject to a budget of feature modification cost while minimizing the number of queries, where each query returns only a class and confidence score.