A Graph Based Multilingual Word Sense Disambiguation
J. H. Patil1, S. N. Patankar2
1Jyotsna Harshal Patil, Department of Computer Engineering, Datta Meghe College of Engineering, Airoli Thane (Maharashtra), India.
2Prof. S. N. Patankar, Associate Professor, Department of Computer Engineering, Datta Meghe College of Engineering, Airoli Thane (Maharashtra), India.
Manuscript received on 8 February 2018 | Revised Manuscript received on 15 February 2018 | Manuscript Published on 28 February 2018 | PP: 11-16 | Volume-7 Issue-5, February 2018 | Retrieval Number: E2491027518/18©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Nowadays, the need of advanced free text filtering is increasing. Therefore, when searching for specific keywords, it is desirable to eliminate occurrences where the word or words are used in an inappropriate sense. This task could be exploited in internet browsers, and resource discovery systems, relational databases containing free text fields, electronic document management systems, data warehouse and data mining systems, etc. In order to resolve this problem in this work, we present joint approach to Word Sense Disambiguation (WSD). Our method exploits IndoWordNet, is a linked lexical knowledge base of word nets of 18 scheduled languages of India, a very large knowledge base, to perform graph based WSD across different languages in India, and brings together empirical evidence from these languages using ensemble methods. Therefore the results show that, by complementing the wide-coverage lexical knowledge with robust graph-based algorithms and combination methods, we can achieve the state of the art in WSD settings. However, it does not require any sort of training process, no hand-coding of lexical entries, nor the hand-tagging of texts.
Keywords: Word Sense Disambiguation, Indoword Net, Graph Based Approach, Multilingual Information.
Scope of the Article: Graph Algorithms and Graph Drawing