Local Homology of Word Embeddings
This work addresses the gap in applying TDA to NLP, offering a novel approach for researchers in computational linguistics, though it appears incremental as it builds on existing TDA methods.
The paper tackled the problem of analyzing word embeddings in NLP by applying topological data analysis (TDA) tools, specifically using local homology to develop an unsupervised algorithm that shows potential for word sense disambiguation.
Topological data analysis (TDA) has been widely used to make progress on a number of problems. However, it seems that TDA application in natural language processing (NLP) is at its infancy. In this paper we try to bridge the gap by arguing why TDA tools are a natural choice when it comes to analysing word embedding data. We describe a parallelisable unsupervised learning algorithm based on local homology of datapoints and show some experimental results on word embedding data. We see that local homology of datapoints in word embedding data contains some information that can potentially be used to solve the word sense disambiguation problem.