An Experimental Survey on Parsing with Neural and Finite Automata Networks
Parsing is the process of structuring a linear depiction in
accordance with a given grammar. The “linear depiction” may
be a language sentence, a computer program, a weaving pattern,
a sequence of biological strata, a part of music, actions in a ritual
performance, in short any linear chain in which the preceding
elements in some way confine the next element. Parsing with
finite automata networks implies, in one way, the conversion of
a regular expression into a minimal deterministic finite
automaton, while parsing with neural networks involves parsing
of a natural language sentence. This research paper presents a
twofold investigation on the various parsing techniques with (i)
neural networks and (ii) finite automata networks. Consequently,
the present research paper depicts a comprehensive comparison
among a number of parsing techniques with neural networks
followed by another in depth comparison flanked by a number
of parsing techniques with finite automata networks.
Keywords: Neural networks, Finite automata networks, Parsing, Regular expressions, Natural language processing
Download Full-Text