17th of September, 13:00 (Swedish time)
Watch this seminar on YouTube
Title: Interpreting and Grounding Pre-trained Representations for Natural Language Processing
Building computers that understand human language is one of the central goals in artificial intelligence. A recent breakthrough on the way towards this goal is the development of powerful language representation models based on deep learning. However, while these models have substantially advanced the state of the art in natural language processing (NLP) for a wide range of tasks, our understanding of the learned representations and our repertoire of techniques for integrating them with other knowledge representations and modalities remain limited.
This talk will give an introduction to our two recently started projects "Interpreting and Grounding Pre-trained Representations for Natural Language Processing" and "Representation Learning for Conversational AI", where we will develop new models that explore synergies between language representations and modalities of different types as well as analysis methods to investigate properties of learned representations. We will give a high-level introduction to the overall goals of these projects and then highlight some recent work where we investigate the effects of multimodal training where language representation models can learn from images in addition to text.
About the speaker: Richard Johansson a senior lecturer at the Division of Data Science and Artificial Intelligence at the Department of Computer Science and Engineering, Chalmers Technical University and University of Gothenburg. He earned his PhD in 2008 at Lund University and then spent some years as a postdoctoral researcher at the University of Trento, Italy, before returning to Sweden in 2011. His research interests are at the intersection of natural language processing and machine learning (ML), and most of his research focuses on the interplay between structured knowledge and ML-based language processing. His recent projects include two collaborations funded by Wallenberg AI, Autonomous Systems and Software Program (WASP) that aim to develop general ML models for written text and spoken dialogue as well as new analysis methods for these models.
17 September, 2021, 13:00
17 September, 2021, 13:45