Title : Directed Locomotion for Modular Robots with Evolvable Morphologies
| Presenter | Gongjin Lan |
| Abstract | We are investigating an evolutionary robotic system where robot morphologies and controllers can evolve. In such a system newborn robots face the problem of having to learn to control their own body that is a random combination of the bodies of the parents. This paper focuses on learning an elementary skill: walking in a given direction. To this end, we apply the HyperNEAT algorithm guided by a fitness function that balances the distance travelled in a direction and the deviation between the desired and the actually travelled directions. We validate the generality and scalability of this method on a test suite of nine modular robots with evolvable morphologies in different shapes and sizes. The experimental results show that the best controllers obtained this way produce trajectories that accurately follow the correct direction and reach a considerable distance within 60 seconds |
Title : Systematic Study of Long Tail Phenomena in Entity Linking
| Presenter | Filip Ilievski |
| Abstract | State-of-the-art entity linkers achieve high accuracy scores with probabilistic methods. However, these scores should be considered in relation to the properties of the datasets they are evaluated on. Until now, there has not been a systematic investigation of the properties of entity linking datasets and their impact on system performance. We report on a series of hypotheses regarding the long tail phenomena in entity linking datasets, their interaction, and their impact on system performance. Our systematic study of these hypotheses shows that evaluation datasets mainly capture head entities and only incidentally cover data from the tail, thus encouraging systems to overfit to popular/frequent and non-ambiguous cases. We find the most difficult cases of entity linking among the infrequent candidates of ambiguous forms. With our findings, we hope to inspire future designs of both entity linking systems and evaluation datasets. To support this goal, we provide a list of recommended actions for better inclusion of tail cases. |