The paper presents a visual language that can help users of a context-aware application represent the current situation, or situations they wish detected, in a language that is both formally defined, and readable and understandable by humans and machines alike. Inspired from Regular Expressions, the concept of Extended Concept Pattern provides both conciseness and expressive power, allowing for...

Independent, heterogeneous, distributed, sometimes transient and mobile data sources produce an enormous amount of information that should be semantically integrated and filtered, or, as we say, tailored, based on the users’ interests and context. We propose to exploit knowledge about the user, the adopted device, and the environment altogether called context to the end of information tailoring...

Extended context-free grammars are context-free grammars in which the right-hand sides of productions are allowed to be any regular language rather than being restricted to be any nite language. We develop a novel approach to top-down predictive parser construction for extended context-free grammars that is based on rewriting of partial syntax trees. This work is motivated by our development of...

Recently it has been shown that the class of BPA (or context-free) processes can be widely used to describe sequential processes and to define their semantics. This class has been intensively studied. Bisimilarity and regularity appeared to be decidable within the BPA processes (see [CHS95], [BCS96]). We extend these processes with a deadlocking state into BPA systems. We show that the BPA clas...

We investigate the use of extended context in attention-based neural machine translation. We base our experiments on translated movie subtitles and discuss the effect of increasing the segments beyond single translation units. We study the use of extended source language context as well as bilingual context extensions. The models learn to distinguish between information from different segments ...

Depression is defined as a mood condition. One key problem in depression’s clinical description is determining how persistent mood changes influence emotional reactivity to ongoing environmental stimuli. Repeatedly, depressed individuals have been observed to exhibit diminished reactivity to change in the emotional context. These observations have spawned a theory called emotion context insensi...

Unlike traditional recurrent neural networks, the Long ShortTerm Memory (LSTM) model generalizes well when presented with training sequences derived from regular and also simple nonregular languages. Our novel combination of LSTM and the decoupled extended Kalman filter, however, learns even faster and generalizes even better, requiring only the 10 shortest exemplars (n ≤ 10) of the context sen...