Szczegóły publikacji
Opis bibliograficzny
Biologically inspired linguistic habit graph networks used for text correction / Marcin GADAMER, Adrian HORZYK // W: Recent developments and achievements in biocybernetics and biomedical engineering : proceedings of the 20th Polish Conference on Biocybernetics and Biomedical Engineering, Kraków, Poland, September 20-22, 2017 / eds. Piotr Augustyniak, Roman Maniewski, Ryszard Tadeusiewicz. — [Cham] : Springer International Publishing, cop. 2018. — (Advances in Intelligent Systems and Computing ; ISSN 2194-5357 ; vol. 647). — ISBN: 978-3-319-66904-5; e-ISBN: 978-3-319-66905-2. — S. 304–314. — Bibliogr. s. 313–314, Abstr. — Publikacja dostępna online od: 2017-08-20
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 109394 |
|---|---|
| Data dodania do BaDAP | 2017-10-24 |
| Tekst źródłowy | URL |
| DOI | 10.1007/978-3-319-66905-2_27 |
| Rok publikacji | 2018 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | 20th Polish Conference on Biocybernetics and Biomedical Engineering |
| Czasopismo/seria | Advances in Intelligent Systems and Computing |
Abstract
This paper describes a biologically inspired Linguistic Habit Graphs (LHG) which could be used as a new way of storing, compressing, and processing sentences. The common letter and word orders from sentences are used to construct a special neural graph that is able to associate and memorize the natural human linguistic habits. The used algorithms can learn from texts written by people and transform the information of orders, frequencies, and contexts into a graph structure, labeled vertices with word properties, and weighted connections. Vertices of this graph are reactive to input data as well as neurons in biological brains. The way in which the human brain works is an inspiration for many known algorithms from contemporary computer science. In the brain, there is no time and no place for nested loops and other time consuming classic algorithms and computational techniques. Based on this approach, we developed new algorithms. They use a graph structure to perform a semi–automatic spell checking and text correction. The above mentioned functionalities of this model are always available in constant time. © 2018, Springer International Publishing AG.
