A Word Sense Disambiguation Approach for Converting Natural Language Text into a Common Semantic Description

Tacoa, Francisco; Uchida, Hiroshi; Ishizuka, Mitsuru

doi:10.1109/icsc.2010.66

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, if the word relationship appears near the word doctor and patient, we can say that its meaning related to ‗Doctrines' and not ‗Education' which is known as sentential context [2]. At a onetime Computer that read words, must use a process called word sense disambiguation to find the correct meaning of a word [3].…”

Section: Introductionmentioning

confidence: 99%

Performance Improvement of Context Identification for Human Computer Interaction

2016

IJSR

View full text Add to dashboard Cite

Context Identification is a task of identifying intended sense (meaning) of word based on context, has been a prominent research work of Natural Language Processing for Word Sense Disambiguation (WSD). Human Computer Interaction (HCI) is useful to improve users and computers interactions by making it more usable. For this improvement, combination of Supervised and Unsupervised WSD methods are used. Under this framework, the words from ambiguous sentences have categorized for finding the appropriate sense of given word, amounts to correct domain of word among the number of domain representing its correct sense. While interacting with the system, sentence or instruction provided to the computer should be well analyzed and understood properly, such that there should be no confusion. It is useful for Human Computer Interaction (HCI) as a self learning process or language which provides people with the ability to explore themselves. For effective disambiguation, these methods find to be more helpful in the various areas that demands human computer interaction. Also, it motivates the people of ruler areas for self learning English language. In this paper, the results of unsupervised learning are reported. Also, the accuracy of this work is calculated with the aim of finding best suitable domain of word for WSD. It shows that combination of supervised and unsupervised approach improves accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%