Natural language reasoning is a complex task that requires understanding the meaning of natural language expressions and recognizing semantic relations between them. The course is organized around this interdisciplinary problem and exploits methods from formal logic.
 
Most of the course is dedicated to logic-based approaches to natural language reasoning, in particular, how one can automatically detect that a premise sentence semantically entails or contradicts a hypothesis sentence. This includes systematic translation of the natural language meaning in some formal logic, i.e, a formal language with formal semantics, and use of theorem-proving techniques for automated reasoning.

The course also discusses empirical methods where evaluation datasets for natural language reasoning is covered: from their creation (either manually, automatically or semi-automatically) to the semantic challenges they contain. Such evaluation datasets contain a mixture of logic-style deductive inferences and inferences requiring common sense and world knowledge. The state of the art in natural language reasoning is also be covered.

The first part of the course covers the theories, methods, and assignments related to natural language reasoning and provides students with background knowledge that will be sufficient to carry out final group project and write a short paper. The projects most likely will be a software project where a group of students is expected to answer a research question in the domain of natural language reasoning.

N.B. You can enroll in this course via Osiris during the 'wijzigingsdagen' of the Humanities faculty: 24th and 25th of October 2022.
N.B. Inschrijven in Osiris voor deze cursus is mogelijk op 24 en 25 oktober 2022 tijdens de wijzigingsdagen van de faculteit Geesteswetenschappen (GW).