Text-mining the neurosynth corpus using deep boltzmann machines

TY - CHAP

T1 - Text-mining the neurosynth corpus using deep boltzmann machines

AU - Monti, Ricardo

AU - Lorenz, Romy

AU - Leech, Robert

AU - Anagnostopoulos, Christoforos

AU - Montana, Giovanni

PY - 2016/8/24

Y1 - 2016/8/24

N2 - 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.

AB - 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.

KW - Deep Boltzmann machines

KW - Meta-Analysis

KW - text-mining

KW - topic models

UR - http://www.scopus.com/inward/record.url?scp=84988872592&partnerID=8YFLogxK

U2 - 10.1109/PRNI.2016.7552329

DO - 10.1109/PRNI.2016.7552329

M3 - Conference paper

AN - SCOPUS:84988872592

BT - PRNI 2016 - 6th International Workshop on Pattern Recognition in Neuroimaging

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Workshop on Pattern Recognition in Neuroimaging, PRNI 2016

Y2 - 22 June 2016 through 24 June 2016

ER -