Context-Aware Text Matching Algorithm for Korean Peninsula Language Knowledge Base Based on Density Clustering

Abstract

The majority of the traditional methods deal with text matching at the word level which remains uncertain as the text semantic features are ignored. This also leads to the problems of low recall and high space utilization of text matching while the comprehensiveness of matching results is poor. The resultant method, thus, cannot process long text and short text simultaneously. The current study proposes a text matching algorithm for Korean Peninsula language knowledge base based on density clustering. Using the deep multiview semantic document representation model, the semantic vector of the text to be matched is captured for semantic dependency which is utilized to extract the text semantic features. As per the feature extraction outcomes, the text similarity is calculated by subtree matching method, and a semantic classification model based on SWEM and pseudo-twin network is designed for semantic text classification. Finally, the text matching of Korean Peninsula language knowledge base is carried out by applying density clustering algorithm. Experimental results show that the proposed method has high matching recall rate with low space requirements and can effectively match long and short texts concurrently.

Natural Language Processing of Grammar Checker Tools for Academic Writing: A Systematic Literature Review

“…Does the article discuss further Grammar construction or language fluency? [1,7,8]); the year 2018 (1 paper with the reference number of [18]); the year 2019 (4 documents with the reference number of [2,3,4,19]); the year 2020 (1 paper with the reference number of [5]); and year 2021 (10 documents with the reference number of [6,9,10,11,12,13,14,15,16,17]).…”

“…The list of tools that the gathered papers used are the Word2Vec deep learning tool, TAALES or Tool for the Automatic Assessment of Lexical Sophistication [7] , and Scikit-learn [4] . 8 out of the 20 research papers used the Word2Vec tool as a deep learning tool (8 documents with the reference number of [1,2,4,6,9,11,19,20]). The Word2Vec tool has been widely used for natural language processing since 2013.…”

“…The compilation of the research papers has varying algorithms from each other, where each algorithm is based on its use and purpose. Most algorithms are pattern matching or searching algorithms based on a corpus or dictionary: the Wu-Manber Algorithm [19] (hashing technique) and Ah-Corasick algorithm [9] (string-searching). Furthermore, other algorithms used are the VF2 algorithm [11] (graph-matching algorithm), backpropagation algorithm [16] (quickly calculate derivatives in a graph), LDA [14] (The Latent Dirichlet Allocation extracts definition from a word) algorithm, and the others are generic algorithms that the researchers created and proposed.…”