Abstract
This paper introduces a novel approach to tackle the existing gap on message translations in dialogue systems. Currently, submitted messages to the dialogue systems are considered as isolated sentences. Thus, missing context information impede the disambiguation of homographs words in ambiguous sentences. Our approach solves this disambiguation problem by using concepts over existing ontologies.
Highlights
The ability of people to communicate each other becomes increasingly important due to the conducting of trade agreements, implementation of academic activities, or just aiming the intention of a relationship [1]
During a dialogue, homographs terms can occur, i.e. words which have the same spelling but different meanings. These words may generate ambiguity at the time of translation because, according to Bar-Hillel [3], the flow for selecting the meaning of given homograph word in an automated translation tool relies on a statistical algorithm
The results suggest the approach has useful function to disambiguate the homographs in dialogue and it got to show the relevance in using semantic web technologies as knowledge-base to machine translation when applied in a dialogue
Summary
The ability of people to communicate each other becomes increasingly important due to the conducting of trade agreements, implementation of academic activities, or just aiming the intention of a relationship [1]. Translating homographs in sentences into dialogue is a challenging task: most translation techniques, such as Transfer-based, Example-based, Statistical are developed for retrieving the translation based on frequency algorithms [4]. These algorithms are designed to decide through pre-established criteria, which is the better translation. You need to buy a “cachimbo” or a “tubo”, both in the English language are written the same way, but when we translate into Portuguese is described in more than one word depending on the context [13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Artificial Intelligence & Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
