The paper examines the benefits and the drawbacks of two competing approaches to natural language processing: statistical (probabilistic) and symbolic (deterministic). While the statistical approach is gaining popularity, better results may often be obtained using symbolic methodologies. The paper argues that the benefits of consistent deterministic parsers and lexica are well worth the time an...

thinking was related to interactions in the symbolic world. Considering visual representations and the operations taken place when people interact with them, the ‘external cognition’ perspective was explored for assessing more effectively how technological innovations in graphical representations should be approached. The ‘external cognition’ perspective focuses on the cognitive processing invo...

This paper uses longitudinal data from the Dutch OSA Labor Supply Panel (1980-2000) to examine the phenomenon of unemployment scarring in the Netherlands. The study extends current research by not only asking if earlier unemployment damages subsequent employment careers and wages but also explores variation by the level of unemployment insurance benefits and key individual characteristics such ...

I discuss the literature and benefits of symbolic calculation in the life sciences; some ways to develop the field; and a way to model sequential processes.

We propose a new cognitive robot control architecture in which the cognitive layer can be programmed by means of the agent programming language Goal. The architecture exploits the support that agent-oriented programming offers for creating cognitive robotic agents, including symbolic knowledge representation, deliberation via modular, high-level action selection, and support for multiple, decla...

While most of the literature on Black men prescribe to a deficit model that focuses on academic failures and poverty, this work focuses on the positive by profiling Black men who have successfully entered information technology (IT) majors. Here we reveal various capitals, their accumulation, and their effects using Bourdieu’s framework to inductively uncover that Black men succeed in IT career...

Partial evaluation, also known as automatic specialization, is a particular collection of techniques for improving the performance of an application. With clear benefits, but unclear implementation up until now, partial evaluation is little used in current computing practice. This soon will change. Presented here is partial execution, an alternative to symbolic evaluation the technique driving ...

The performance of symbolic inference tasks has long been a challenge to connectionists.In this paper, we present an extended survey of this area. Existing connectionist inference systems are reviewed, with particular reference to how they perform variable binding and rule-based reasoning and whether they involve distributed or localist representations. The benefits and disadvantages of differe...

Casting neural network weights in symbolic terms is crucial for interpreting and explaining the behavior of a network. Additionally, in some domains, a symbolic description may lead to more robust generalization. We present a principled approach to symbolic rule extraction based on the notion of weight templates, parameterized regions of weight space corresponding to specific symbolic expressio...