Events

Lecture

Prof. Dipl.-Ing. Dr.techn. Bernhard Pfahringer, University of Waikato

Everything Changes, but Your ML Models Stay the Same?

Machine learning assumes data to be independently and identically sampled from a distribution, though in the real world this assumption rarely holds. Data stream mining …

Lecture

Mag. Dr. Stephanie Gross, MSc, OFAI

Multimodal Human–Robot Interaction in Situated Task Descriptions

Humans and robots are increasingly working together at home and in the workplace, and successful interaction depends on the robot picking up on the human's …

Lecture

Dr. Peter Hallman, MA, BA, OFAI

Comparatives in Arabic

Syrian Arabic, like English, has a syntactic constraint on the formation of clauses that describe standards of comparison. But unlike in English, the scope of …

Lecture

Univ.-Prof. Dr.-Ing. Benjamin Roth, BSc, MSc, University of Vienna

Evaluation and Learning with Structured Test Sets

While behavioural tests capture human prior knowledge and insights, there has been little exploration on how to leverage them for model training and development. This …

Lecture

Ass.-Prof. Dr. Karën Fort, Sorbonne Université / LORIA

Ethics and NLP: What we Talk About, What we Don't Talk About Anymore, What we Never Talked About

Commercial applications of natural language processing have now invaded our daily lives, with consequences that raise difficult ethical questions. These questions will be discussed in …

Lecture

Dipl.-Psych. Dr. Christoph Scheepers, University of Glasgow

The “Crossword Effect” in Free Word Recall: A Retrieval Advantage for Words Encoded in Line with their Spatial Associations

Word concepts are known to modulate sensori-motor responses, but it is less understood how sensori-motor actions influence access to word concepts in memory. This phenomenon …

Lecture

Dr. Raphael Deimel, BSc, MSc, TU Wien

Fluent and Intuitive Human–robot Object Handover

Watching humans hand over things, the skill seems trivial. But the smoothness and the ease of interaction is deceiving, as complex, fast and nonverbal communication …

Lecture

Dipl.-Ing. Dr. techn. Roman Pflugfelder, TU München / Technion

Fragmented Occlusion in Computer Vision

Computer vision algorithms are stymied by occlusion, the result of information loss when a three-dimensional scene is projected onto a two-dimensional image. A new video …

Lecture

Prof. Antti Arppe, MSc, PhD, University of Alberta

Finding Words that Aren't There: Using Word Embeddings to Improve Dictionary Search for Low-resource Languages

Machine learning for language technology requires an amount of training data that simply does not exist for many languages. Can we exploit existing models for …

Lecture

Prof. Dr. (i.V.) Steffen Eger, Bielefeld University

Text Generation for the Humanities

Can computers learn to write poetry in particular styles, or to summarize historical documents using more modern language? These and other subjects will be discussed …