We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Word sense disambiguation for Punjabi language using deep learning techniques.
- Authors
Singh, Varinder pal; Kumar, Parteek
- Abstract
Word sense disambiguation (WSD) identifies the right meaning of the word in the given context. It is an indispensable and critical application for all the natural language processing tasks. In this paper, two deep learning techniques multilayer perceptron and long short-term memory (LSTM) have been individually inspected on the word vectors of 66 ambiguous Punjabi nouns for an explicit WSD system of Punjabi language. The inputs to the deep learning techniques are the simple word vectors derived directly from manually sense-tagged corpus of Punjabi language. The multilayer perceptron has outperformed the LSTM deep learning technique for WSD task of Punjabi language. Six traditional supervised machine learning techniques have also been tested on same dataset using unigram and bigram feature sets. A comparison between deep learning techniques and traditional six supervised machine learning techniques clearly indicates that the deep learning techniques using simple word vectors outperforms the earlier techniques.
- Subjects
DEEP learning; SUPERVISED learning; MACHINE learning; SEMANTICS; NATURAL language processing; SHORT-term memory
- Publication
Neural Computing & Applications, 2020, Vol 32, Issue 8, p2963
- ISSN
0941-0643
- Publication type
Article
- DOI
10.1007/s00521-019-04581-3