A Method for Taxonomy-Aware Embeddings Evaluation (Student Abstract)

Authors

  • Navid Nobani University of Milano-Bicocca
  • Lorenzo Malandri University of Milano-Bicocca
  • Fabio Mercorio University of Milano-Bicocca
  • Mario Mezzanzanica University of Milano-Bicocca

Keywords:

Embedding-evaluation, Word Embeddings, Semantic Web

Abstract

While word embeddings have been showing their effectiveness in capturing semantic and lexical similarities in a large number of domains, in case the corpus used to generate embeddings is associated with a taxonomy (i.e., classification tasks over standard de-jure taxonomies) the common intrinsic and extrinsic evaluation tasks cannot guarantee that the generated embeddings are consistent with the taxonomy. This, as a consequence sharply limits the use of distributional semantics in those domains. To address this issue, we design and implement MEET, which proposes a new measure -HSS- that allows evaluating embeddings from a text corpus preserving the semantic similarity relations of the taxonomy.

Downloads

Published

2021-05-18

How to Cite

Nobani, N., Malandri, L., Mercorio, F., & Mezzanzanica, M. (2021). A Method for Taxonomy-Aware Embeddings Evaluation (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15859-15860. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17926

Issue

Section

AAAI Student Abstract and Poster Program