首页|Recent Research from Alliance University Highlight Findings in Machine Learning (Word Sense Disambiguation Corpus for Kashmiri)

Recent Research from Alliance University Highlight Findings in Machine Learning (Word Sense Disambiguation Corpus for Kashmiri)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews-Data detailed on Machine Learning have been prese nted. According to news reporting from Bangalore,India, by NewsRx journalists, research stated, "Ambiguity is considered an indispensable attributeof all natu ral languages. The process of associating the precise interpretation to an ambig uous wordtaking into consideration the context in which it occurs is known as w ord sense disambiguation (WSD)."The news correspondents obtained a quote from the research from Alliance Univers ity, "Supervisedapproaches to WSD are showing better performance in contrast to their counterparts. These approaches,however, require sense annotated corpus t o carry out the disambiguation process. This paper presentsthe first-ever stand ard WSD dataset for the Kashmiri language. The raw corpus used to develop the sense annotated dataset is collected from different resources and contains about 1 M tokens. The senseannotatedcorpus is then created using this raw corpus for 124 commonly used ambiguous Kashmiri words.Kashmiri WordNet, an important lexic al resource for the Kashmiri language, is used for obtaining thesenses used in the annotation process. The developed sense-tagged corpus is multifarious in nat ure andhas 19,854 sentences. Based on this annotated corpus, the Lexical Sample WSD task for Kashmiri is carriedout using different machine-learning algorithm s (J48, IBk, Naive Bayes, Dl4jMlpClassifier, SVM). To trainthese models for the WSD task, bag-of-words (BoW) and word embeddings obtained using the Word2Vecmo del are used. We used different standard measures, viz. accuracy, precision, rec all, and F1-measure,to calculate the performance of these algorithms. Different machine learning algorithms reported differentvalues for these measures on usi ng different features."

BangaloreIndiaAsiaAlgorithmsCybo rgsEmerging TechnologiesMachine LearningWord Sense DisambiguationAllianc e University

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Oct.31)