A great deal of research efiort is currently being made in the realm of natural computing. Natural computing mainly focuses on the definition, formal description, analysis, simulation and programming of new models of computation (usually with the same expressive power as Turing Machines) inspired by Nature. It also concerns algorithms inspired by natural processes, which are especially accurate for problems dealing with complex systems or approximate solutions.
These new models have difierent interests. Firstly, their main features, like intrinsic parallelism/distributivity, makes them particularly suitable for the simu- lation of complex systems. Secondly, they could lead to a new paradigm of com- puters, which is particularly important, as the von Neumann architecture and its conventional implementation with silicon-based technologies is reaching its theoret- ical limits. Last but not least, their parallel nature makes them capable of treating NP problems eficiently.
However, they also have some counterparts. Most of them consist of many ele- ments behaving in a coordinated fashion, creating a global complex behaviour from very simple local decisions. For this reason, the fundamentals of their functioning are often dificult to understand. In the same manner, the task of designing or programming these kinds of devices faces many dificulties.
During our work, we have tried to contribute to this field of research by develop- ing and studying a framework for the simulation and programming of a bio-inspired computing model called Networks of Evolutionary Processors (NEPs) [Castellanos et al., 2001]. We have also investigated its application to NP problems and to the field of Natural Language Processing. In addition, since designing and program- ming NEPs and other natural systems is a complex task, we have proposed and studied a general methodology that permits the automatic design or programming of complex systems. This methodology is based on the Grammatical Evolution (GE) algorithm and its modern variants like Christiansen Grammar Evolution or Attribute Grammar Evolution [Echeandia et al., 2005]. GE is an algorithm inspired by the natural process of evolution and natural selection.

https://repositorio.uam.es/xmlui/bitstream/handle/10486/662031/rosal_garcia_emilio_del.pdf;sequence=1

Real life applications of bio-inspired computing models: EAP and NEPs

PNEPs (Parsing Networks of Evolutionary Processors) extend NEPs with context free (instead of substituting) rules, leftmost derivation, bad terminals check and indexes to rebuild the derivation tree. It is possible to build a PNEP from any context free grammar without additional constraints, able to generate all the different derivations for ambiguous grammars with a temporal performance bound by the depth of the derivation tree. One of the main difficulties encountered by parsing techniques when building complete parsing trees for natural languages is the spatial and temporal performance of the analysis. Shallow parsing tries to overcome these difficulties. The goal of shallow parsing is to analyze the main components of the sentences (for example, noun groups, verb groups, etc.) rather than complete sentences. The current paper is mainly focused on testing the suitability of PNEPs to shallow parsing.

Emilio del Rosal García

Papers

PNEPs for Shallow Parsing - NEPs Extended for Parsing Applied to Shallow Parsing.