@article{3cb35d06-aca3-4329-ba93-be092ecc3b27,
author = {Artur Niewiarowski},
title = {Short text similarity algorithm based on the edit distance and thesaurus},
journal = {Czasopismo Techniczne},
volume = {2016},
number = {Nauki Podstawowe Zeszyt 1-NP 2016},
year = {2016},
issn = {0011-4561},
pages = {159-173},keywords = {Levenshtein distance algorithm; the edit distance; thesaurus; the measure of texts similarity; plagiarism detection; text mining; Natural Language Processing; Natural Language Understanding; stemming; lemmatization},
abstract = {This paper proposes a method of comparing the short texts using the Levenshtein distance algorithm and thesaurus for analysing terms enclosed in texts instead of popular methods exploiting the grammatical variations glossary. The tested texts contain a variety of nouns and verbs together with grammatical or orthographical mistakes. Based on the proposed new algorithm the similarity of such texts will be estimated. The described technique is compared with methods: Cosine distances, distance Dice and Jaccard distance constructed on the term frequency method. The proposition is competitive against well-known algorithms of stemming and lemmatization.},
doi = {10.4467/2353737XCT.16.149.5760},
url = {https://ejournals.eu/czasopismo/czasopismo-techniczne/artykul/short-text-similarity-algorithm-based-on-the-edit-distance-and-thesaurus}
}