Text-mining the NeuroSynth corpus using Deep Boltzmann Machines
This work addresses text-mining for neuroimaging meta-analysis, offering an incremental improvement over existing methods like word counts and Latent Dirichlet Allocation.
The authors tackled the problem of text-mining the NeuroSynth neuroimaging corpus by applying Deep Boltzmann Machines, which learned embeddings with clear semantic structure to facilitate machine learning techniques.
Large-scale automated meta-analysis of neuroimaging data has recently established itself as an important tool in advancing our understanding of human brain function. This research has been pioneered by NeuroSynth, a database collecting both brain activation coordinates and associated text across a large cohort of neuroimaging research papers. One of the fundamental aspects of such meta-analysis is text-mining. To date, word counts and more sophisticated methods such as Latent Dirichlet Allocation have been proposed. In this work we present an unsupervised study of the NeuroSynth text corpus using Deep Boltzmann Machines (DBMs). The use of DBMs yields several advantages over the aforementioned methods, principal among which is the fact that it yields both word and document embeddings in a high-dimensional vector space. Such embeddings serve to facilitate the use of traditional machine learning techniques on the text corpus. The proposed DBM model is shown to learn embeddings with a clear semantic structure.