We present a flexible method that rearranges the ranked output of compound splitters (i.e., decomposers of one-word compounds such as the German Kinderlied ‘children’s song’) using a distributional semantics model. In an experiment, we show that our re-ranker improves the quality of various compound splitters.

Techniques that exploit knowledge of distributional similarity between words have been proposed in many areas of Natural Language Processing. For example, in language modeling, the sparse data problem can be alleviated by estimating the probabilities of unseen co-occurrences of events from the probabilities of seen co-occurrences of similar events. In other applications, distributional similari...

In this review, we take an extensive look at the role that principles of causality and passivity have played in various areas physics engineering, including modern field metamaterials. The aim is not to provide a comprehensive list references as number would be thousands, but review major results contributions which animated these unified framework could useful understanding developments differ...

Distributional Reinforcement Learning (RL) maintains the entire probability distribution of reward-to-go, i.e. return, providing more learning signals that account for uncertainty associated with policy performance, which may be beneficial trading off exploration and exploitation in general. Previous works distributional RL focused mainly on computing state-action-return distributions, here we ...