NORMA eResearch @NCI Library

Named Entity Recognition on Kannada Low Resource Language using Deep Learning Models

Kulkarni, Pavan (2021) Named Entity Recognition on Kannada Low Resource Language using Deep Learning Models. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (743kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Entity extraction with Kannada language recognition is a difficult task that requires adept knowledge of the literature. The language is influenced by other languages. Around 60 million people in Karnataka, India, can understand and speak. Kannada is classified as a low-resource language. Because the shortage of data makes it a difficult assignment to complete. Many tests have been conducted and have shown important results in the English language. In contrast to English, the Kannada language does not capitalize words. For contribution to Kannada Named Entity Recognition (NER) Bi-directional long short-term memory (Bi-LSTM), Bi-directional Encoder Representations from Transformers (BERT) and Random Forest Classifier (RFC) models are used. The accuracy obtained from Bi-LSTM is 0.9624 and 0.7985 accuracy and precision of 0.78 from RFC for the B-DATE entity.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Bi-LSTM; BERT; Random Forest Classifier; Entity extraction
Subjects: P Language and Literature > PL Languages and literatures of Eastern Asia, Africa, Oceania
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 06 Dec 2021 12:55
Last Modified: 06 Dec 2021 12:55

Actions (login required)

View Item View Item