Word Sense Disambiguation using Bidirectional LSTM

Please use this identifier to cite or link to this item: http://idr.nitk.ac.in/jspui/handle/123456789/15124

Full metadata record

DC Field	Value	Language
dc.contributor.author	Rakshith J.
dc.contributor.author	Savasere S.
dc.contributor.author	Ramachandran A.
dc.contributor.author	Akhila P.
dc.contributor.author	Koolagudi S.G.
dc.date.accessioned	2021-05-05T10:16:30Z	-
dc.date.available	2021-05-05T10:16:30Z	-
dc.date.issued	2019
dc.identifier.citation	2019 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2019 - Proceedings , Vol. , , p. -	en_US
dc.identifier.uri	https://doi.org/10.1109/DISCOVER47552.2019.9008031
dc.identifier.uri	http://idr.nitk.ac.in/jspui/handle/123456789/15124	-
dc.description.abstract	Word Sense Disambiguation is considered one of the challenging problems in natural language processing(NLP). LSTM-based Word Sense Disambiguation techniques have been shown effective through experiments. Models have been proposed before that employed LSTM to achieve state-of-the-art results. This paper presents an implementation and analysis of a Bidirectional LSTM model using openly available datasets (Semcor, MASC, SensEval-2 and SensEval-3) and knowledge base (WordNet). Our experiments showed that a similar state of the art results could be obtained with much less data or without external resources like knowledge graphs and parts of speech tagging. © 2019 IEEE.	en_US
dc.title	Word Sense Disambiguation using Bidirectional LSTM	en_US
dc.type	Conference Paper	en_US
Appears in Collections:	2. Conference Papers

Files in This Item:

There are no files associated with this item.