Compositional matrix-space models of language: Definitions, properties, and learning methods

Abstract

We give an in-depth account of compositional matrix-space models (CMSMs), a type of generic models for natural language, wherein compositionality is realized via matrix multiplication. We argue for the structural plausibility of this model and show that it is able to cover and combine various common compositional natural language processing approaches. Then, we consider efficient task-specific learning methods for training CMSMs and evaluate their performance in compositionality prediction and sentiment analysis.

Efficient Axiomatization of OWL 2 EL Ontologies from Data by Means of Formal Concept Analysis

“…However, some of these embeddings fail to capture the se-mantics (Jain, Kalo, Balke, Krestel 2021) and, in effect, a large amount of useless, false predictions might be generated. This major issue can possibly be remedied by novel embedding approaches (Abboud, Ceylan, Lukasiewicz, Salvatori 2020;Asaadi, Giesbrecht, Rudolph 2023).…”