Vector-Space Models of Semantic Representation From a Cognitive Perspective: A Discussion of Common Misconceptions

Models that represent meaning as high-dimensional numerical vectors—such as latent semantic analysis (LSA), hyperspace analogue to language (HAL), bound encoding of the aggregate language environment (BEAGLE), topic models, global vectors (GloVe), and word2vec—have been introduced as extremely powerful machine-learning proxies for human semantic representations and have seen an explosive rise in popularity over the past 2 decades. However, despite their considerable advancements and spread in the cognitive sciences, one can observe problems associated with the adequate presentation and understanding of some of their features. Indeed, when these models are examined from a cognitive perspective, a number of unfounded arguments tend to appear in the psychological literature. In this article, we review the most common of these arguments and discuss (a) what exactly these models represent at the implementational level and their plausibility as a cognitive theory, (b) how they deal with various aspects of meaning such as polysemy or compositionality, and (c) how they relate to the debate on embodied and grounded cognition. We identify common misconceptions that arise as a result of incomplete descriptions, outdated arguments, and unclear distinctions between theory and implementation of the models. We clarify and amend these points to provide a theoretical basis for future research and discussions on vector models of semantic representation.

[1]  Kent Johnson,et al.  An Overview of Lexical Semantics , 2007 .

[2]  Jon A. Willits,et al.  Models of Semantic Memory , 2015 .

[3]  G. Bower,et al.  From conditioning to category learning: an adaptive network model. , 1988, Journal of experimental psychology. General.

[4]  Max M. Louwerse,et al.  What's Up can be Explained by Language Statistics , 2013, CogSci.

[5]  P. Perruchet,et al.  Implicit learning and statistical learning: one phenomenon, two approaches , 2006, Trends in Cognitive Sciences.

[6]  A. Tversky,et al.  On the psychology of prediction , 1973 .

[7]  Angeliki Lazaridou,et al.  Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world , 2014, ACL.

[8]  Mirella Lapata,et al.  Measuring Distributional Similarity in Context , 2010, EMNLP.

[9]  Felipe Munoz-Rubke,et al.  A new statistical model for analyzing rating scale data pertaining to word meaning , 2017, Psychological Research.

[10]  Michael P. Kaschak,et al.  Putting words in perspective , 2004, Memory & cognition.

[11]  Fritz Günther,et al.  Latent semantic analysis cosines as a cognitive similarity measure: Evidence from priming studies , 2016, Quarterly journal of experimental psychology.

[12]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[13]  Thomas L. Griffiths,et al.  Evaluating Vector-Space Models of Word Representation, or, The Unreasonable Effectiveness of Counting Words Near Other Words , 2017, CogSci.

[14]  C. Osgood The nature and measurement of meaning. , 1952, Psychological bulletin.

[15]  Guillaume Lample,et al.  Evaluation of Word Vector Representations by Subspace Alignment , 2015, EMNLP.

[16]  Kris Heylen,et al.  Monitoring Polysemy: Word Space Models as a Tool for Large-Scale Lexical Semantic Analysis , 2015 .

[17]  L. Barsalou,et al.  Whither structured representation? , 1999, Behavioral and Brain Sciences.

[18]  Michael W. Berry,et al.  Mathematical Foundations Behind Latent Semantic Analysis , 2007 .

[19]  J. Gottlieb Attention, Learning, and the Value of Information , 2012, Neuron.

[20]  Emiel van Miltenburg,et al.  Sound-based distributional models , 2015, IWCS.

[21]  Max M. Louwerse,et al.  A Taste of Words: Linguistic Context and Perceptual Simulation Predict the Modality of Words , 2011, Cogn. Sci..

[22]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[23]  W. Schneider,et al.  Perceptual Knowledge Retrieval Activates Sensory Brain Regions , 2006, The Journal of Neuroscience.

[24]  Alessandro Lenci,et al.  Identifying hypernyms in distributional semantic spaces , 2012, *SEMEVAL.

[25]  A. Greenwald,et al.  Measuring individual differences in implicit cognition: the implicit association test. , 1998, Journal of personality and social psychology.

[26]  Georgiana Dinu,et al.  DISSECT - DIStributional SEmantics Composition Toolkit , 2013, ACL.

[27]  Eugene Albert Nida,et al.  A Componential Analysis of Meaning: An Introduction to Semantic Structures , 1979 .

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

[29]  Danielle S. McNamara,et al.  Handbook of latent semantic analysis , 2007 .

[30]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[31]  R Ratcliff,et al.  Memory-based language processing: psycholinguistic research in the 1990s. , 1998, Annual review of psychology.

[32]  William Dyer Grampp The classical view , 1965 .

[33]  Magnus Sahlgren,et al.  The Distributional Hypothesis , 2008 .

[34]  Gemma Boleda,et al.  Regular polysemy: A distributional model , 2012, *SEM@NAACL-HLT.

[35]  Victor Kuperman,et al.  Individual Variability in the Semantic Processing of English Compound Words , 2017, Journal of experimental psychology. Learning, memory, and cognition.

[36]  Mark Sadoski,et al.  Reading Comprehension is Embodied: Theoretical and Practical Considerations , 2018 .

[37]  Sudeep Bhatia Associative Judgment and Vector Space Semantics , 2017, Psychological review.

[38]  Geoff Hollis,et al.  Estimating the average need of semantic knowledge from distributional semantic models , 2017, Memory & Cognition.

[39]  Lera Boroditsky,et al.  Semantic Coherence Facilitates Distributional Learning. , 2017, Cognitive science.

[40]  H. Hoffman,et al.  Unconscious acquisition of complex procedural knowledge. , 1987 .

[41]  Xiaoping P. Hu,et al.  fMRI evidence for word association and situated simulation in conceptual processing , 2008, Journal of Physiology-Paris.

[42]  M. Piazza,et al.  The neuro-cognitive representations of symbols: the case of concrete words , 2017, Neuropsychologia.

[43]  W. Kintsch,et al.  High-Dimensional Semantic Space Accounts of Priming. , 2006 .

[44]  I. Martin,et al.  Classical conditioning of human 'evaluative' responses. , 1975, Behaviour research and therapy.

[45]  James L. McClelland,et al.  Concepts, Control, and Context: A Connectionist Account of Normal and Disordered Semantic Cognition , 2018, Psychological review.

[46]  Luc Steels,et al.  Open-ended Procedural Semantics , 2012, Language Grounding in Robots.

[47]  Steve Majerus,et al.  The non-strategic nature of linguistic long-term memory effects in verbal short-term memory , 2018, Journal of Memory and Language.

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

[49]  Rolf A. Zwaan,et al.  Language Encodes Geographical Information , 2009, Cogn. Sci..

[50]  Walter Kintsch Similarity as a function of semantic distance and amount of knowledge. , 2014, Psychological review.

[51]  Marco Marelli,et al.  ‘Understanding’ differs between English and German: Capturing systematic language differences of complex words , 2019, Cortex.

[52]  Max M. Louwerse,et al.  Symbol Interdependency in Symbolic and Embodied Cognition , 2011, Top. Cogn. Sci..

[53]  Georgiana Dinu,et al.  Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors , 2014, ACL.

[54]  Michael N Jones,et al.  Representing word meaning and order information in a composite holographic lexicon. , 2007, Psychological review.

[55]  Cyrus Shaoul,et al.  Exploring lexical co-occurrence space using HiDEx , 2010, Behavior research methods.

[56]  B. Murdock A Theory for the Storage and Retrieval of Item and Associative Information. , 1982 .

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

[58]  Gabriella Vigliocco,et al.  Integrating experiential and distributional data to learn semantic representations. , 2009, Psychological review.

[59]  Barbara Kaup,et al.  Is there a difference between stripy journeys and stripy ladybirds? The N400 response to semantic and world-knowledge violations during sentence processing , 2016, Brain and Cognition.

[60]  Michael J Cortese,et al.  Predicting semantic priming at the item level , 2008 .

[61]  Benoît Lemaire,et al.  Incremental Construction of an Associative Network from a Corpus , 2004 .

[62]  A G Barto,et al.  Toward a modern theory of adaptive networks: expectation and prediction. , 1981, Psychological review.

[63]  A. Tversky,et al.  Extensional versus intuitive reasoning: the conjunction fallacy in probability judgment , 1983 .

[64]  Rolf A. Zwaan,et al.  Embodied Sentence Comprehension , 2005 .

[65]  R. Baayen,et al.  Learning is not decline: The mental lexicon as a window into cognition across the lifespan , 2014 .

[66]  Stephen Clark,et al.  Grounding Semantics in Olfactory Perception , 2015, ACL.

[67]  Zellig S. Harris,et al.  Distributional Structure , 1954 .

[68]  R. Rescorla,et al.  A theory of Pavlovian conditioning : Variations in the effectiveness of reinforcement and nonreinforcement , 1972 .

[69]  Michael Spranger The co-evolution of basic spatial terms and categories , 2012 .

[70]  Stefanie Tellex,et al.  The Human Speechome Project , 2006, EELC.

[71]  M. Steyvers Combining Feature Norms and Text Data with Topic Models , 2022 .

[72]  James L. McClelland,et al.  Structure and deterioration of semantic memory: a neuropsychological and computational investigation. , 2004, Psychological review.

[73]  M. Brysbaert,et al.  The Word Frequency Effect in Word Processing: An Updated Review , 2018 .

[74]  Stephen Clark,et al.  Multi- and Cross-Modal Semantics Beyond Vision: Grounding in Auditory Perception , 2015, EMNLP.

[75]  Ton Dijkstra,et al.  Context-dependent Semantic Processing in the Human Brain: Evidence from Idiom Comprehension , 2013, Journal of Cognitive Neuroscience.

[76]  T. Landauer LSA as a Theory of Meaning , 2007 .

[77]  M. Brysbaert,et al.  Explaining human performance in psycholinguistic tasks with models of semantic similarity based on prediction and counting : A review and empirical validation , 2017 .

[78]  A. Jacobs,et al.  Models of visual word recognition: Sampling the state of the art. , 1994 .

[79]  Magnus Sahlgren,et al.  An Introduction to Random Indexing , 2005 .

[80]  Michael P. Kaschak,et al.  Activity and Imagined Activity Can Enhance Young Children's Reading Comprehension. , 2004 .

[81]  F. Binkofski,et al.  The challenge of abstract concepts. , 2017, Psychological bulletin.

[82]  J. de Houwer,et al.  Associative learning of likes and dislikes: a review of 25 years of research on human evaluative conditioning. , 2001, Psychological bulletin.

[83]  P. Hagoort,et al.  Integration of Word Meaning and World Knowledge in Language Comprehension , 2004, Science.

[84]  Peter D. Turney Similarity of Semantic Relations , 2006, CL.

[85]  Lawrence W. Barsalou,et al.  Perceptions of perceptual symbols , 1999, Behavioral and Brain Sciences.

[86]  Fritz Günther,et al.  LSAfun - An R package for computations based on Latent Semantic Analysis , 2014, Behavior Research Methods.

[87]  Michael N. Jones,et al.  Perceptual Inference Through Global Lexical Similarity , 2012, Top. Cogn. Sci..

[88]  John R. Anderson,et al.  Reflections of the Environment in Memory Form of the Memory Functions , 2022 .

[89]  Roberto Basili,et al.  Towards Compositional Tree Kernels , 2013, JSSP.

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

[91]  Vladimir M. Sloutsky,et al.  An associative account of the development of word learning , 2017, Cognitive Psychology.

[92]  G Gigerenzer,et al.  Reasoning the fast and frugal way: models of bounded rationality. , 1996, Psychological review.

[93]  Bart Geurts,et al.  Scalar Diversity , 2016, J. Semant..

[94]  J. M. Kittross The measurement of meaning , 1959 .

[95]  M. Marelli,et al.  Affixation in semantic space: Modeling morpheme meanings with compositional distributional semantics. , 2015, Psychological review.

[96]  Steve R. Howell,et al.  A Model of Grounded Language Acquisition: Sensorimotor Features Improve Lexical and Grammatical Learning. , 2005 .

[97]  Harold Bekkering,et al.  How specifically are action verbs represented in the neural motor system: An fMRI study , 2010, NeuroImage.

[98]  Chris Westbury,et al.  Pay no attention to that man behind the curtain: Explaining semantics without semantics , 2016 .

[99]  Max M. Louwerse,et al.  Archaeology Through Computational Linguistics: Inscription Statistics Predict Excavation Sites of Indus Valley Artifacts , 2016, Cogn. Sci..

[100]  Carol S. Dweck,et al.  Motivational processes affecting learning. , 1986 .

[101]  Marco Marelli,et al.  Enter sandman: Compound processing and semantic transparency in a compositional perspective. , 2019, Journal of experimental psychology. Learning, memory, and cognition.

[102]  Mirella Lapata,et al.  Composition in Distributional Models of Semantics , 2010, Cogn. Sci..

[103]  T. Goldberg,et al.  Quantifying incoherence in speech: An automated methodology and novel application to schizophrenia , 2007, Schizophrenia Research.

[104]  Francisco Pereira,et al.  A comparative evaluation of off-the-shelf distributed semantic representations for modelling behavioural data , 2016, Cognitive neuropsychology.

[105]  Yoed N. Kenett,et al.  The Semantic Distance Task: Quantifying Semantic Distance With Semantic Network Path Length , 2017, Journal of experimental psychology. Learning, memory, and cognition.

[106]  Christian Biemann,et al.  Text: now in 2D! A framework for lexical expansion with contextual similarity , 2013, J. Lang. Model..

[107]  Pawel Lewicki,et al.  Processing Information About Covariations That Cannot Be Articulated , 1986 .

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

[109]  Walter Kintsch,et al.  Predication , 2001, Cogn. Sci..

[110]  Omer Levy,et al.  Linguistic Regularities in Sparse and Explicit Word Representations , 2014, CoNLL.

[111]  Roel M. Willems,et al.  Grounding the neurobiology of language in first principles: The necessity of non-language-centric explanations for language comprehension , 2018, Cognition.

[112]  Carlo Caltagirone,et al.  The contribution of neurodegenerative diseases to the modelling of semantic memory: A new proposal and a review of the literature , 2015, Neuropsychologia.

[113]  Linda B. Smith,et al.  The importance of shape in early lexical learning , 1988 .

[114]  Omer Levy,et al.  Neural Word Embedding as Implicit Matrix Factorization , 2014, NIPS.

[115]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[116]  Patrick Pantel,et al.  Discovering word senses from text , 2002, KDD.

[117]  F. Pulvermüller,et al.  Abstract semantics in the motor system? – An event-related fMRI study on passive reading of semantic word categories carrying abstract emotional and mental meaning , 2017, Cortex.

[118]  Gabriel Recchia,et al.  More data trumps smarter algorithms: Comparing pointwise mutual information with latent semantic analysis , 2009, Behavior research methods.

[119]  Marco Baroni,et al.  Frege in Space: A Program for Composition Distributional Semantics , 2014, LILT.

[120]  Patrick F. Reidy An Introduction to Latent Semantic Analysis , 2009 .

[121]  T. Hascher Learning and Emotion: Perspectives for Theory and Research , 2010 .

[122]  Ewald Lang,et al.  5. Two-level Semantics: Semantic Form and Conceptual Structure , 2019, Semantics - Theories.

[123]  Sudeep Bhatia,et al.  The semantic representation of prejudice and stereotypes , 2017, Cognition.

[124]  Charles A. Perfetti,et al.  The limits of co‐occurrence: Tools and theories in language research , 1998 .

[125]  Marco Baroni,et al.  Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space , 2010, EMNLP.

[126]  Laurence A. Marschall,et al.  Pay No Attention to the Man Behind the Curtain , 1996 .

[127]  W. Kintsch Metaphor comprehension: A computational theory , 2000, Psychonomic bulletin & review.

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

[129]  S. Grossberg The Link between Brain Learning, Attention, and Consciousness , 1999, Consciousness and Cognition.

[130]  Ray Jackendoff,et al.  Précis of Foundations of language: brain, meaning, grammar, evolution. , 2003, The Behavioral and brain sciences.

[131]  P. Johnson-Laird,et al.  Mental Models: Towards a Cognitive Science of Language, Inference, and Consciousness , 1985 .

[132]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[133]  B. Bahrami,et al.  Coming of age: A review of embodiment and the neuroscience of semantics , 2012, Cortex.

[134]  Michael P. Kaschak,et al.  Grounding language in action , 2002, Psychonomic bulletin & review.

[135]  Eleanor Rosch Heider,et al.  The structure of the color space in naming and memory for two languages , 1972 .

[136]  Lori Buchanan,et al.  Grounding co-occurrence: Identifying features in a lexical co-occurrence model of semantic memory , 2009, Behavior research methods.

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

[138]  P. Tabossi Accessing lexical ambiguity in different types of sentential contexts , 1988 .

[139]  Mark S. Seidenberg,et al.  Semantic feature production norms for a large set of living and nonliving things , 2005, Behavior research methods.

[140]  Eileen Kintsch,et al.  Summary Street: Interactive Computer Support for Writing , 2004 .

[141]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[142]  Scott P. Johnson,et al.  Visual statistical learning in infancy: evidence for a domain general learning mechanism , 2002, Cognition.

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

[144]  Angeliki Lazaridou,et al.  Multimodal Word Meaning Induction From Minimal Exposure to Natural Text. , 2017, Cognitive science.

[145]  Christina L. Gagné,et al.  Compounding as Abstract Operation in Semantic Space: Investigating relational effects through a large-scale, data-driven computational model , 2017, Cognition.

[146]  Alessandro Lenci,et al.  Distributional semantics in linguistic and cognitive research , 2008 .

[147]  Douglas L. Medin,et al.  3. The Classical View , 1981 .

[148]  Guillermo Jorge-Botana,et al.  Visualizing polysemy using LSA and the predication algorithm , 2010, J. Assoc. Inf. Sci. Technol..

[149]  C Ronchi,et al.  The tree of knowledge , 2014 .

[150]  A. Glenberg,et al.  Symbol Grounding and Meaning: A Comparison of High-Dimensional and Embodied Theories of Meaning , 2000 .

[151]  Michael N. Jones,et al.  Redundancy in Perceptual and Linguistic Experience: Comparing Feature-Based and Distributional Models of Semantic Representation , 2010, Top. Cogn. Sci..

[152]  Marco Marelli,et al.  Social Media and Language Processing: How Facebook and Twitter Provide the Best Frequency Estimates for Studying Word Recognition , 2016, Cogn. Sci..

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

[154]  Michael P. Kaschak,et al.  Constructing Meaning: The Role of Affordances and Grammatical Constructions in Sentence Comprehension , 2000 .

[155]  John A Bullinaria,et al.  Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD , 2012, Behavior Research Methods.

[156]  Michael N. Jones,et al.  Experience as a Free Parameter in the Cognitive Modeling of Language , 2016, CogSci.

[157]  Alessandro Lenci,et al.  Distributional Models of Word Meaning , 2018 .

[158]  Arvind Narayanan,et al.  Semantics derived automatically from language corpora contain human-like biases , 2016, Science.

[159]  José Camacho-Collados,et al.  From Word to Sense Embeddings: A Survey on Vector Representations of Meaning , 2018, J. Artif. Intell. Res..

[160]  Max M. Louwerse,et al.  Time after Time in Words: Chronology through Language Statistics , 2015, CogSci.

[161]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[162]  Dermot Lynott Can We Model Conceptual Combination using Distributional Information ? , 2004 .

[163]  R N Aslin,et al.  Statistical Learning by 8-Month-Old Infants , 1996, Science.

[164]  Max M. Louwerse,et al.  Representing Spatial Structure Through Maps and Language: Lord of the Rings Encodes the Spatial Structure of Middle Earth , 2012, Cogn. Sci..

[165]  Paul Buitelaar,et al.  Ontology Learning from Text: An Overview , 2005 .

[166]  Victor R. Prybutok,et al.  Latent Semantic Analysis: five methodological recommendations , 2012, Eur. J. Inf. Syst..

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

[168]  J. Firth,et al.  Papers in linguistics, 1934-1951 , 1957 .

[169]  Ricardo Olmos,et al.  Transforming Selected Concepts Into Dimensions in Latent Semantic Analysis , 2014 .

[170]  Kristina Hansson,et al.  Quantifying Semantic Linguistic Maturity in Children , 2015, Journal of Psycholinguistic Research.

[171]  Winston D. Goh,et al.  An item-level analysis of lexical-semantic effects in free recall and recognition memory using the megastudy approach , 2018, Quarterly journal of experimental psychology.

[172]  Chong Wang,et al.  Reading Tea Leaves: How Humans Interpret Topic Models , 2009, NIPS.

[173]  Geoff Hollis,et al.  The principals of meaning: Extracting semantic dimensions from co-occurrence models of semantics , 2016, Psychonomic Bulletin & Review.

[174]  Ramón Fernández Astudillo,et al.  Not All Contexts Are Created Equal: Better Word Representations with Variable Attention , 2015, EMNLP.

[175]  J. Gray,et al.  PERSONALITY AND REINFORCEMENT IN ASSOCIATIVE AND INSTRUMENTAL LEARNING , 1995 .

[176]  Dorothee J. Chwilla,et al.  When Heuristics Clash with Parsing Routines: ERP Evidence for Conflict Monitoring in Sentence Perception , 2006, Journal of Cognitive Neuroscience.

[177]  Trevor Cohen,et al.  Empirical distributional semantics: Methods and biomedical applications , 2009, J. Biomed. Informatics.

[178]  James L. McClelland,et al.  You shall know an object by the company it keeps: An investigation of semantic representations derived from object co-occurrence in visual scenes , 2015, Neuropsychologia.

[179]  Michael Wolmetz,et al.  Conceptual knowledge representation: A cross-section of current research , 2016, Cognitive neuropsychology.

[180]  F. Pulvermüller A brain perspective on language mechanisms: from discrete neuronal ensembles to serial order , 2002, Progress in Neurobiology.

[181]  W. Kintsch The role of knowledge in discourse comprehension: a construction-integration model. , 1988, Psychological review.

[182]  Sanjeev Arora,et al.  Learning Topic Models -- Going beyond SVD , 2012, 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science.

[183]  Constantine Sedikides,et al.  A Latent Semantic Analysis of Gender Stereotype-Consistency and Narrowness in American English , 2009 .

[184]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[185]  J. Saffran Statistical Language Learning , 2003 .

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

[187]  Geoffrey Zweig,et al.  Combining Heterogeneous Models for Measuring Relational Similarity , 2013, NAACL.

[188]  Robert M. French,et al.  Four Problems with Extracting Human Semantics from Large Text Corpora , 2019, Proceedings of the Twenty-Fourth Annual Conference of the Cognitive Science Society.

[189]  A. Glenberg Few believe the world is flat: How embodiment is changing the scientific understanding of cognition. , 2015, Canadian journal of experimental psychology = Revue canadienne de psychologie experimentale.

[190]  Arthur M. Glenberg,et al.  Constraint on covariation: It's not meaning , 2008 .

[191]  Elia Bruni,et al.  Multimodal Distributional Semantics , 2014, J. Artif. Intell. Res..

[192]  A. Glenberg,et al.  Symbols and Embodiment: Debates on Meaning and Cognition , 2008 .

[193]  Allan Collins,et al.  A spreading-activation theory of semantic processing , 1975 .

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

[195]  Antske Fokkens,et al.  Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell , 2018, BlackboxNLP@EMNLP.

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

[197]  Angeliki Lazaridou,et al.  Combining Language and Vision with a Multimodal Skip-gram Model , 2015, NAACL.

[198]  Marco Marelli,et al.  Understanding Karma Police: The Perceived Plausibility of Noun Compounds as Predicted by Distributional Models of Semantic Representation , 2016, PloS one.

[199]  Simon Dennis,et al.  How to use the LSA website , 2005 .

[200]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[201]  Daniel Barbará,et al.  On-line LDA: Adaptive Topic Models for Mining Text Streams with Applications to Topic Detection and Tracking , 2008, 2008 Eighth IEEE International Conference on Data Mining.