A joint team from the Ubiquitous Knowledge Processing Lab (UKP) and the Austrian Research Institute for Artificial Intelligence (OFAI) participated in Humor Analysis based on Human Annotation (HAHA 2019), a shared task at the Iberian Languages Evaluation Forum (IberLEF 2019). The goal of the shared task was to predict humour in Spanish-language Twitter posts.

A paper describing the team's system, “OFAI–UKP at HAHA@IberLEF2019: Predicting the Humorousness of Tweets Using Gaussian Process Preference Learning”, will appear in the IberLEF proceedings. The IberLEF workshop, co-located with the 2019 Conference of the Spanish Society for Natural Language Processing (SEPLN2019), will be held on September

24, 2019 in Bilbao, Spain.

The system and paper were jointly authored by UKP members Erik-Lân Do Dinh, Dr. Edwin Simpson, and Prof. Iryna Gurevych, and by Dr. Tristan Miller of OFAI.