Natural Language Processing
DESCRIPTION
Natural Language Processing has seen important advances over the past decade. While deep learning models have achieved impressive performance, even demonstrating common-sense knowledge, they are commonly viewed as uninterpretable black-boxes. We combine deep learning with deductive reasoning techniques from the symbolic Artificial Intelligence tradition, to produce new algorithms capable of reaching conclusions requiring multiple inference steps, using premises and conclusions expressed in natural language. We are also interested in understanding multilingual language models. While neural multilingual language models (MLMs) have notable success, their internal mechanics remain quite unclear. We explore symbolic approaches to understand the inner workings of large MLMs and investigate how to inject linguistic knowledge into neural models, aiming to learn how to benefit from human expertise and work with sparse data.
RESEARCHERS
Alexandros Potamianos
National Technical University of Athens, Greece & HERON Robotics Center of Excellence, Greece
Angela Ralli
University of Patras, Greece
Antonios Anastasopoulos
George Mason University, USA
Christos H. Papadimitriou
Columbia University, USA
Dimitris Galanis
Athena Research Center, Greece
Grigorios Tsoumakas
Aristotle University of Thessaloniki, Greece
Ion (Ioannis) Androutsopoulos
Athens University of Economics and Business, Greece
John Pavlopoulos
Αthens University of Economics and Business, Greece
Katerina Pastra
Athena Research Center, Greece
Manolis Koubarakis
National and Kapodistrian University of Athens, Greece
Nikos Vasilakis
Brown University, USA
Panagiotis Tsaparas
University of Ioannina, Greece
Pantelis John (PJ) Beaghton
Imperial College London, UK
Sophia Ananiadou
University of Manchester, UK
Stella Markantonatou
Athena Research Center, Greece
