A Graph-Based Approach to the Disambiguation of Multiple Languages
2021
There is a growing need for sophisticated free text filtering in today's world, and this demand is reflected in the abstract.Consequently, it is preferable to exclude instances when the phrase or words are used in an incorrect meaning when doing a search using those terms.Internet browsers, resource finding tools, relational databases with free-text fields, electronic document management, data warehousing, data mining, etc. might all benefit from this work.In this paper, we propose a collaborative method for resolving such ambiguities in words, called Word Sense Disambiguation (WSD).In order to implement graph-based WSD across several Indian languages, our technique makes use of IndoWordNet, a connected lexical knowledge base comprising word nets of 18 scheduled languages of India, a very big knowledge base.Therefore, the results demonstrate that we may attain state-of-the-art in WSD contexts by combining the extensive lexical knowledge with strong graph-based algorithms and combination approaches.However, no manual training, lexical entry hand-coding, or textual entity labelling is required.