BabelRelate! A Joint Multilingual Approach to Computing Semantic Relatedness

Authors

  • Roberto Navigli Sapienza Università di Roma
  • Simone Paolo Ponzetto Sapienza Università di Roma

DOI:

https://doi.org/10.1609/aaai.v26i1.8119

Keywords:

Semantic Networks, Multilinguality, Semantic Relatedness

Abstract

We present a knowledge-rich approach to computing semantic relatedness which exploits the joint contribution of different languages. Our approach is based on the lexicon and semantic knowledge of a wide-coverage multilingual knowledge base, which is used to compute semantic graphs in a variety of languages. Complementary information from these graphs is then combined to produce a 'core' graph where disambiguated translations are connected by means of strong semantic relations. We evaluate our approach on standard monolingual and bilingual datasets, and show that: i) we outperform a graph-based approach which does not use multilinguality in a joint way; ii) we achieve uniformly competitive results for both resource-rich and resource-poor languages.

Downloads

Published

2021-09-20

How to Cite

Navigli, R., & Ponzetto, S. P. (2021). BabelRelate! A Joint Multilingual Approach to Computing Semantic Relatedness. Proceedings of the AAAI Conference on Artificial Intelligence, 26(1), 108-114. https://doi.org/10.1609/aaai.v26i1.8119