Published April 22, 2021 | Version v2
Conference paper Open

A Domain Independent Semantic Measure for Keyword Sense Disambiguation

  • 1. Everis/NTT Data
  • 2. University of Zaragoza

Description

Understanding the user’s intention is crucial in human-machine interaction.When dealing with text input, Word Sense Disambiguation (WSD) techniques play an important role. WSD techniques typically require well-formed sentences as context to operate, and predefined catalogues of word senses. However, such conditions do not always
apply, such as when there is a need to disambiguate keywords from a query, or sets of tags describing any Web resource. In this paper, we propose a keyword disambiguation method based on the semantic relatedness between words and ontological terms. Taking advantage of the semantic information captured by word  mbeddings, our approach maps a set of input keywords to their meanings within a given target ontology.We focus on situations where the available linguistic information is very scarce, hampering natural language based approaches. Experimental results show the feasibility of our approach without previous training for target domains

Files

3412841.3442141.pdf

Files (1.1 MB)

Name Size Download all
md5:c8086bc8a2ab282cb5d68c8ee5ddf9c5
1.1 MB Preview Download

Additional details

Funding

Pret-a-LLOD – Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors 825182
European Commission
Lynx – Building the Legal Knowledge Graph for Smart Compliance Services in Multilingual Europe 780602
European Commission