Algorithms 2013, 6(3), 565-590; doi:10.3390/a6030565
Article

An Emergent Approach to Text Analysis Based on a Connectionist Model and the Web

Department of Information Engineering, University of Pisa, Largo Lucio Lazzarino 1, Pisa 56122, Italy
* Author to whom correspondence should be addressed.
Received: 5 August 2013; in revised form: 5 September 2013 / Accepted: 10 September 2013 / Published: 17 September 2013
PDF Full-text Download PDF Full-Text [899 KB, uploaded 17 September 2013 17:30 CEST]
Abstract: In this paper, we present a method to provide proactive assistance in text checking, based on usage relationships between words structuralized on the Web. For a given sentence, the method builds a connectionist structure of relationships between word n-grams. Such structure is then parameterized by means of an unsupervised and language agnostic optimization process. Finally, the method provides a representation of the sentence that allows emerging the least prominent usage-based relational patterns, helping to easily find badly-written and unpopular text. The study includes the problem statement and its characterization in the literature, as well as the proposed solving approach and some experimental use.
Keywords: natural language processing; language usage; emergent paradigm; unsupervised approach; connectionist model; web as corpus

Article Statistics

Load and display the download statistics.

Citations to this Article

Cite This Article

MDPI and ACS Style

Cimino, M.G.; Vaglini, G. An Emergent Approach to Text Analysis Based on a Connectionist Model and the Web. Algorithms 2013, 6, 565-590.

AMA Style

Cimino MG, Vaglini G. An Emergent Approach to Text Analysis Based on a Connectionist Model and the Web. Algorithms. 2013; 6(3):565-590.

Chicago/Turabian Style

Cimino, Mario G.; Vaglini, Gigliola. 2013. "An Emergent Approach to Text Analysis Based on a Connectionist Model and the Web." Algorithms 6, no. 3: 565-590.

Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert