Learning Taxonomies of Concepts and not Words using Contextualized Word Representations: A Position Paper
This addresses a problem in NLP for researchers and practitioners by offering a potential improvement in taxonomy learning, but it is incremental as it builds on existing contextualized word representations.
The paper tackles the limitation of current taxonomy learning systems that define concepts as single words by proposing a novel approach using contextualized word representations to define concepts as synsets and measure similarity and hypernymy, with no concrete results or numbers provided.
Taxonomies are semantic hierarchies of concepts. One limitation of current taxonomy learning systems is that they define concepts as single words. This position paper argues that contextualized word representations, which recently achieved state-of-the-art results on many competitive NLP tasks, are a promising method to address this limitation. We outline a novel approach for taxonomy learning that (1) defines concepts as synsets, (2) learns density-based approximations of contextualized word representations, and (3) can measure similarity and hypernymy among them.