首页|Study Data from Debre Markos University Update Understanding of Intelligent Syst ems (Enhancing Word Sense Disambiguation for Amharic homophone words using Bidir ectional Long Short-Term Memory network)
Study Data from Debre Markos University Update Understanding of Intelligent Syst ems (Enhancing Word Sense Disambiguation for Amharic homophone words using Bidir ectional Long Short-Term Memory network)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on intelligent systems is now available. According to news reporting originating from Debre Markos Univers ity by NewsRx correspondents, research stated, “Given the Amharic language has a lot of perplexing terminology since it features duplicate homophone letters, fi del’s ha, , and xe (three of which are pronounced as HA), sze and se (both prono unced as SE), and (both pronounced as AE), and tse and (both pronounced as TSE). ” Our news reporters obtained a quote from the research from Debre Markos Universi ty: “The WSD (Word Sense Disambiguation) model, which tackles the issue of lexic al ambiguity in the context of the Amharic language, is developed using a deep l earning technique. Due to the unavailability of the Amharic wordnet, a total of 1756 examples of paired Amharic ambiguous homophonic words were collected. These words were dihi ti(dhnet) and dixi ti(dhnet), ri(m’hur) and hhuri(m’hur), be (b e’al) and bezhi (be’al), biyi (abiy) and biyi(abiy), with a total of 1756 exampl es. Following word preprocessing, word2vec, fasttext, Term Frequency-Inverse Doc ument Frequency (TFIDF), and bag of words (BoW) were used to vectorize the text. The vectorized text was divided into train and test data. The train data was th en analysed using Naive Bayes (NB), K-nearest neighbour (KNN), logistic regressi on (LG), decision trees (DT), random forests (RF), and random oversampling techn ique.”
Debre Markos UniversityEmerging Techno logiesIntelligent SystemsMachine LearningWord Sense Disambiguation
NETL
NSTL
