Computer Science ATLAS talk - Learning from Disagreements
Dates: | 8 December 2021 |
Times: | 14:00 - 15:00 |
What is it: | Seminar |
Organiser: | Department of Computer Science |
Who is it for: | University staff, Adults, Current University students |
Speaker: | , Massimo Poesio |
|
Please join us for our forthcoming Atlas Talk (online) in Computer Science
Joining details:
https://zoom.us/j/98513350116
Passcode 910561
Title - Learning from Disagreements
Speaker - Professor Massimo Poesio (joint work with Alexandra Uma, Dina Almanea, Tommaso Fornaciari, Dirk Hovy, Silviu Paun, and Barbara Plank)
Hosts - Professor Sophia Ananiadou & Professor Angelo Cangelosi
Abstract
There is plenty of evidence from NLP and Computer Vision (CV) that humans disagreee on many cognitive interpretation tasks, from the simplest tasks such as Part of Speech tagging to more subjective tasks such as classifying an image or deciding whether a proposition follows from certain premises. Although most AI work still relies on the assumption that a single interpretation exists, there has been extensive research in recent years on developing methods for learning from data that do not rely on such assumption. In this talk, I will review the evidence about disagreements and the main datasets that contain such information, discuss the best known approaches to build models from data containing them, and compare them on some of the best datasets to assess how their performance is affected by a dataset’s characteristics.
Speakers
Massimo Poesio
Role: Professor
Organisation: Queen Mary University of London
Biography: Massimo Poesio is a Professor in Computational Linguistics at Queen Mary University of London. His research interests include disagreements in language interpretation; anaphora resolution; the creation of large corpora of semantically annotated data (an area in which he pioneered the use of games-with-a-purpose for anaphora with the development of Phrase Detectives, http://www.phrasedetectives.org); semantic interpretation of verbal and non-verbal communication in interaction; the study of conceptual knowledge using a combination of methods from human language technology and neuroscience; and online deception. http://www.massimopoesio.org http://www.dali-ambiguity.org http://www.universalanaphora.org
Travel and Contact Information
Find event
https://zoom.us/j/98513350116