Automatic spelling error detection and correction for Tigrigna information retrieval: a hybrid approach

Abstract

This paper proposes a hybrid approach to design and implement query spelling error detection and correction (SEDC) for Tigrigna information retrieval (IR). Our approach, which is the main contribution to this work, is fast and robust to achieve better performance and also helps the users to easily insert their corrected queries to retrieve relevant information from the IR. This is achieved by combining the normalized measure of bigram overlap using the Jaccard coefficient (J.C) technique, a dynamic programming algorithm for edit distance, and probability of occurrence, which were used to make suggestions for the misspelt words. Our approach was evaluated on the SEDC subtasks separately. It achieved an F-measure of 98.85% on the spelling error detection subtask and an accuracy of 95.36% on the spelling error correction subtask. Thus, a comparison was conducted between our approach and the existing Tigrigna spell checker. It is found that our approach outperformed the existing spell checker and shows a 5.36% improvement in accuracy. This is by far the most promising result with regard to correcting the misspelt users’ queries and improving the overall performance of the IR.

Morphology-Based Spell Checker for Dawurootsuwa Language

“…Te researchers evaluated and developed a hybrid spell and grammar checker for Punjabi languages and got an average accuracy of 83.5%. Unlike the technological favored language, a number of attempts were also made for the underrepresented Ethiopian languages by diferent researchers [8,[16][17][18]. Tese languages include Amharic, Afaan-Oromo, Tigrigna, and Kaf-Nonoo.…”

“…Another Amharic spellchecker was created utilizing a hybrid technique in which the author created spelling checking tools for the Amharic language. As a result, the system's overall performance in error detection and correction was 98% [16]. Similarly, a morphology-based spellchecker for the Afaan-Oromo language was constructed, with 88.62% lexical recall, 100% mistake recall, and 28.62% precision.…”

“…Some researchers developed spelling checking tools by using these approaches. According to [8,[16][17][18], the morphology-based approach is good for morphologically rich languages, to handle internal infection, derivation, and word compounding. Te morphology-based approach for spell checking has many advantages.…”

“…Test data size Design and implementation of morphology based spell checker [8] 1464 Automatic spelling checker for Amharic language [16] 1314 Morphology based spell checker for Kaf Noonoo language [18] 2743 Automatic Amharic spelling error detection and correction using hybrid approach [16] 500…”

“…Tis is especially true for Ethiopian language like Dawurootsuwa. As a result, some spellchecker tools are made for our local languages like Amharic [16,17], Afaan-Oromo [8], Kaf-Nonoo [18], and Tigrigna language [19] but none for the Dawurootsuwa language.…”