Ondřej Dušek is an assistant professor at the Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University. His research is in the areas of dialogue systems and natural language generation; he specifically focuses on neural-networks-based approaches to these problems and their evaluation. He is also involved in the THEaiTRE project on automatic theatre play generation. Ondřej got his PhD in 2017 at Charles University. Between 2016 and 2018, he worked at the Interaction Lab at Heriot Watt University in Edinburgh, one of the leading groups in dialogue systems and natural-language interaction with computers and robots. There he co-organized the E2E NLG text generation challenge and co-led a team of PhD students in the Amazon Alexa Prize dialogue system competition, which came third in two consecutive years.
Better Supervision for End-to-end Neural Dialogue Systems
While end-to-end neural models have been the research trend in task-oriented dialogue systems in the past years, they still suffer from significant problems: The neural models often produce replies inconsistent with past dialogue context or database results, their replies may be dull and formulaic, and they require large amounts of annotated data to train. In this talk, I will present two of our recent experiments that aim at solving these problems.
First, our end-to-end neural system AuGPT based on the GPT-2 pretrained language model aims at consistency and variability in dialogue responses by using massive data augmentation and filtering as well as specific auxiliary training objectives which check for dialogue consistency. It reached favorable results in terms of both automatic metrics and human judgments (in the DSTC9 competition).
Second, we designed a system that is able to discover relevant dialogue slots (domain attributes) without any human annotation. It uses weak supervision from generic linguistic annotation models (semantic parser, named entities), which is further filtered and clustered. We train a neural slot tagger on the discovered slots, which then reaches state-of-the-art results in dialogue slot tagging without labeled training data. We further show that the discovered slots are helpful for training an end-to-end neural dialogue system.
His talk takes place on Wednesday, December 1, 2021 at 15:00 in “little theater” R211 (next to Kachnicka student club in “Stary Pivovar”). The talk will be streamed live and recorded at https://youtu.be/d1uTFcoEy_g.
Amit Kumar Mishra
Amit Kumar Mishra is, currently, a Professor in the Radar Remote Sensing Group at the University of Cape Town. Prof. Mishra has more than 15 years of experience in the domain of radar and radio system design and applied machine learning. His current interests are around the use of cognitive architectures and advanced signal processing and machine learning to understand radar signals. His H-index (Scopus) is 12. He is also a serial innovator and has six patents to his credit.
Fusing Radar and Telecommunication
Radar and telecommunication systems, even though similar in most of their subsystems, need a substantially different set of algorithms and design to make them work. Multiple reasons have been driving more and more researchers to work on possible ways to make radar and telecommunication systems co-exist, cooperate and if possible to co-design of a hybrid system. In this talk, the author shall discuss some of his research-work around fusing telecommunication and radar systems. The talk shall cover three major ideas, viz. commensal radar, symbiotic radar and CommSense system.
His talk is POSTPONED.
Torsten Sattler received a PhD in Computer Science from RWTH Aachen University, Germany, in 2014 under the supervision of Prof. Bastian Leibe and Prof. Leif Kobbelt. In December 2013, he joined the Computer Vision and Geometry Group of Prof. Marc Pollefeys at ETH Zurich, Switzerland, where he currently is a senior researcher and Marc Pollefeys’ deputy while Prof. Pollefeys is on leave from ETH. His research interests include (large-scale) image-based localization using Structure-from-Motion point clouds, real-time localization and SLAM on mobile devices and for robotics, 3D mapping, Augmented abd Virtual Reality, machine learning, (multi-view) stereo, image retrieval and efficient spatial verification, camera calibration and pose estimation. His current work focuses on making algorithms for localization and mapping “smarter” by incorporating higher-level scene understanding.
Torsten has worked on dense sensing for self-driving cars as part of the V-Charge project. He is currently involved in enabling semantic SLAM and re-localization for gardening robots (as part of the Trimbot2020 project, a EU Horizon 2020 project where he leads the efforts on a workpackage), research for Google’s Tango project, where he leads CVG’s research efforts, and in work on self-driving cars.
Torsten has organized multiple tutorials and workshops at CVPR and ICCV. He regularly serves as a reviewer for the top-conferences in Computer Vision (CVPR, ECCV, ICCV) and Robotics (IROS, ICRA) and is an area chair for CVPR 2018 and 3DV 2018. His talk takes place in POSTPONED.
Miloslav Druckmüller is a Professor of Applied Mathematics at the Institute of mathematics, Faculty of Mechanical Engineering, Brno University of Technology and the head of the Department of Computer Graphics and Geometry. His main interests are numerical methods of image analysis, digital image processing, computer graphics and complex variable analysis. During the last 10 years he has been cooperating widely with the Institute for Astronomy, University of Hawaii in the field of solar coronal plasma research. He created a large archive of K-corona (photospheric light scattered on free electrons) images and temperature maps based on Fe and Ni ions observing based on data obtained during total solar eclipses during last two decades. Nowadays his research is mainly focused on processing and analysis of data obtained by NASA SDO spacecraft. His talk takes place in POSTPONED.
Kevin Köser is a senior researcher at the GEOMAR Helmholtz Centre for Ocean Research, Kiel. His main research interest lies in novel camera-based measurement techniques for (deep) sea environments and processes (3D underwater vision). These help to study resources, to explore and monitor (deep) sea habitats or to assess hazards, e.g. with respect to gas flux or seafloor dynamics. In the past years Dr. Köser has taught the classes 3D Photography and Computer Vision Lab at the Swiss Federal Institute of Technology (ETH Zurich) and has worked as a senior researcher in ETH’s Computer Vision and Geometry Lab on shape and motion extraction from photos and videos, geolocalization and image registration. POSTPONED.