Selecting Corpus-Semantic Models for Neurolinguistic Decoding

Neurosemantics aims to learn the mapping between concepts and the neural activity which they elicit during neuroimaging experiments. Different approaches have been used to represent individual concepts, but current state-of-the-art techniques require extensive manual intervention to scale to arbitrary words and domains. To overcome this challenge, we initiate a systematic comparison of automatically-derived corpus representations, based on various types of textual co-occurrence. We find that dependency parse-based features are the most effective, achieving accuracies similar to the leading semi-manual approaches and higher than any published for a corpus-based model. We also find that simple word features enriched with directional information provide a close-to-optimal solution at much lower computational cost.

[1]  Richard A. Harshman,et al.  Indexing by Latent Semantic Analysis , 1990, J. Am. Soc. Inf. Sci..

[2]  Joakim Nivre,et al.  Single Malt or Blended? A Study in Multilingual Parser Optimization , 2007, EMNLP.

[3]  Massimo Poesio,et al.  Strudel: A Corpus-Based Semantic Model Based on Properties and Types , 2010, Cogn. Sci..

[4]  Surendra Prasad,et al.  Automatic Evaluation of Students’ Answers using Syntactically Enhanced LSA , 2003, HLT-NAACL 2003.

[5]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[6]  Gregory Grefenstette,et al.  Explorations in automatic thesaurus discovery , 1994 .

[7]  Massimo Poesio,et al.  Attribute-Based and Value-Based Clustering: An Evaluation , 2004, EMNLP.

[8]  Dominic Widdows,et al.  Unsupervised methods for developing taxonomies by combining syntactic and statistical information , 2003, NAACL.

[9]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[10]  Petr Sojka,et al.  Software Framework for Topic Modelling with Large Corpora , 2010 .

[11]  Nancy Ide,et al.  The American National Corpus First Release , 2004, LREC.

[12]  Curt Burgess,et al.  Producing high-dimensional semantic spaces from lexical co-occurrence , 1996 .

[13]  Magnus Sahlgren,et al.  The Word-Space Model: using distributional analysis to represent syntagmatic and paradigmatic relations between words in high-dimensional vector spaces , 2006 .

[14]  Massimo Poesio,et al.  EEG responds to conceptual stimuli and corpus semantics , 2009, EMNLP.

[15]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[16]  R. Rapp.  Word sense discovery based on sense descriptor dissimilarity , 2003, MTSUMMIT.

[17]  John Blitzer,et al.  Regularized Learning with Networks of Features , 2008, NIPS.

[18]  Francisco Pereira,et al.  Generating Text from Functional Brain Images , 2011, Front. Hum. Neurosci..

[19]  Mirella Lapata,et al.  Dependency-Based Construction of Semantic Space Models , 2007, CL.

[20]  Anna Korhonen,et al.  Using fMRI activation to conceptual stimuli to evaluate methods for extracting conceptual representations from corpora , 2010, HLT-NAACL 2010.

[21]  Karl J. Friston,et al.  Statistical parametric mapping , 2013 .

[22]  Roger B. Bradford,et al.  An empirical study of required dimensionality for large-scale latent semantic indexing applications , 2008, CIKM '08.

[23]  Hinrich Schütze,et al.  A Vector Model for Syntagmatic and Paradigmatic Relatedness , 1993 .

[24]  Chao Yang,et al.  ARPACK users' guide - solution of large-scale eigenvalue problems with implicitly restarted Arnoldi methods , 1998, Software, environments, tools.

[25]  John B. Goodenough,et al.  Contextual correlates of synonymy , 1965, CACM.

[26]  Dekang Lin,et al.  Automatic Retrieval and Clustering of Similar Words , 1998, ACL.

[27]  Shahram Khadivi,et al.  WordNet Based Features for Predicting Brain Activity associated with meanings of nouns , 2010, HLT-NAACL 2010.

[28]  Mark Steyvers,et al.  Topics in semantic representation. , 2007, Psychological review.

[29]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

[30]  Dekang Lin,et al.  DIRT – Discovery of Inference Rules from Text , 2001 .

[31]  Alessandro Lenci,et al.  Distributional Memory: A General Framework for Corpus-Based Semantics , 2010, CL.

[32]  James R. Curran,et al.  Improvements in Automatic Thesaurus Extraction , 2002, ACL 2002.

[33]  J. Bullinaria,et al.  Extracting semantic representations from word co-occurrence statistics: A computational study , 2007, Behavior research methods.

[34]  W. Montague,et al.  Category norms of verbal items in 56 categories A replication and extension of the Connecticut category norms , 1969 .

[35]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[36]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[37]  Tom Michael Mitchell,et al.  From the SelectedWorks of Marcel Adam Just 2008 Using fMRI brain activation to identify cognitive states associated with perception of tools and dwellings , 2016 .

[38]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL 2006.

[39]  Geoffrey E. Hinton,et al.  Zero-shot Learning with Semantic Output Codes , 2009, NIPS.

[40]  Tom M. Mitchell,et al.  Quantitative modeling of the neural representation of objects: How semantic feature norms can account for fMRI activation , 2011, NeuroImage.

[41]  Estevam R. Hruschka,et al.  Toward an Architecture for Never-Ending Language Learning , 2010, AAAI.

[42]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[43]  Patrick Pantel,et al.  DIRT @SBT@discovery of inference rules from text , 2001, KDD '01.

[44]  Tom M. Mitchell,et al.  Thought Recognition: Predicting and Decoding Brain Activity Using the Zero-Shot Learning Model , 2011 .

[45]  Tom Michael Mitchell,et al.  Predicting Human Brain Activity Associated with the Meanings of Nouns , 2008, Science.

[46]  Chris D. Paice,et al.  Another stemmer , 1990, SIGF.