Similarity Evaluation with Wikipedia Features - Intelligent Information Processing X Access content directly
Conference Papers Year : 2020

Similarity Evaluation with Wikipedia Features

Shahbaz Wasti
  • Function : Author
  • PersonId : 1118807
Yuncheng Jiang
  • Function : Author
  • PersonId : 1118808

Abstract

Wikipedia provides rich semantic features e.g., text, link, and category structure. These features can be used to compute semantic similarity (SS) between words or concepts. However, some existing Wikipedia-based SS methods either rely on a single feature or do not incorporate the underlying statistics of different features. We propose novel vector representations of Wikipedia concepts by integrating their multiple semantic features. We utilize the available statistics of these features in Wikipedia to compute their weights. These weights signify the contribution of each feature in similarity evaluation according to its level of importance. The experimental evaluation shows that our new methods obtain better results on SS datasets in comparison with state-of-the-art SS methods.
Fichier principal
Vignette du fichier
498234_1_En_10_Chapter.pdf (348.44 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03456962 , version 1 (30-11-2021)

Licence

Attribution

Identifiers

Cite

Shahbaz Wasti, Jawad Hussain, Guangjiang Huang, Yuncheng Jiang. Similarity Evaluation with Wikipedia Features. 11th International Conference on Intelligent Information Processing (IIP), Jul 2020, Hangzhou, China. pp.99-104, ⟨10.1007/978-3-030-46931-3_10⟩. ⟨hal-03456962⟩
18 View
8 Download

Altmetric

Share

Gmail Facebook X LinkedIn More