Probing taxonomic and thematic embeddings for taxonomic information

F Klubička, JD Kelleher - arXiv preprint arXiv:2301.10656, 2023 - arxiv.org
Modelling taxonomic and thematic relatedness is important for building AI with
comprehensive natural language understanding. The goal of this paper is to learn more …

Revisiting Random Walks for Learning on Graphs

J Kim, O Zaghen, A Suleymanzade, Y Ryou… - arXiv preprint arXiv …, 2024 - arxiv.org
We revisit a simple idea for machine learning on graphs, where a random walk on a graph
produces a machine-readable record, and this record is processed by a deep neural …

Probing with Noise: Unpicking the Warp and Weft of Taxonomic and Thematic Meaning Representations in Static and Contextual Embeddings

F Klubička - 2022 - arrow.tudublin.ie
The semantic relatedness of words has two key dimensions: it can be based on taxonomic
information or thematic, co-occurrence-based information. These are captured by different …