Can Computers Understand Words Like Humans Do? Comparable Semantic Representation in Neural and Computer Systems
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Semantic representation has been studied independently in neuroscience and computer science. A deep understanding of human neural computations and the revolution to strong artificial intelligence appeal for a joint force in the language domain. To investigate comparable representational formats of lexical semantics between these two complex systems, we used fine temporal resolution neural recordings to create a novel open dataset and innovated analysis methods. Specifically, we evaluated three natural language processing (NLP) models with electroencephalography (EEG) recordings under a semantic priming paradigm. With our novel single-trial analysis method, we found semantic representations generated from computational models significantly correlated with EEG responses at an early stage of a typical semantic processing time window in a two-word semantic priming paradigm. Moreover, three representative computational models differentially predicted EEG responses along the dynamics of word processing. Our study thus developed an objective biomarker for assessing human-like computation in computational models. Our novel framework trailblazed a promising way to bridge across disciplines in the investigation of higher-order cognitive functions in human and artificial intelligence.
Abstract
Semantic representation has been studied independently in neuroscience and computer science. A deep understanding of human neural computations and the revolution to strong artificial intelligence appeal for a joint force in the language domain. To investigate comparable representational formats of lexical semantics between these two complex systems, we used fine temporal resolution neural recordings to create a novel open dataset and innovated analysis methods. Specifically, we evaluated three natural language processing (NLP) models with electroencephalography (EEG) recordings under a semantic priming paradigm. With our novel single-trial analysis method, we found semantic representations generated from computational models significantly correlated with EEG responses at an early stage of a typical semantic processing time window in a two-word semantic priming paradigm. Moreover, three representative computational models differentially predicted EEG responses along the dynamics of word processing. Our study thus developed an objective biomarker for assessing human-like computation in computational models. Our novel framework trailblazed a promising way to bridge across disciplines in the investigation of higher-order cognitive functions in human and artificial intelligence.
참고문헌 (40)
- Anderson, J. R., "A spreading activation theory of memory", Journal of verbal learning and verbal behavior, 22(3), pp.261~295 (1983)
- Balota, D. A., "Automatic semantic activation and episodic memory encoding", Journal of verbal learning and verbal behavior, 22(1), pp.88~104 (1983)
- Bemis, D. K., "Simple composition : A magnetoence phalography investigation into the comprehension of minimal linguistic phrases", Journal of Neuroscience, 31(8), pp.2801~2814 (2011)
- Bentin, S., "Event-related potentials, lexical decision and semantic priming", Electroencephalography and clinical Neurophysiology, 60(4), pp.343~355 (1985)
- Brennan, J., "Naturalistic sentence comprehension in the brain", Language and Linguistics Compass, 10(7), pp.299~313 (2016)
- Broderick, M. P., "Electrophysiological correlates of semantic dissimilarity reflect the comprehension of natural, narrative speech", Current Biology, 28(5), pp.803~809 (2018)
- Brown, C., "The processing nature of the N400 : Evidence from masked priming", Journal of cognitive neuroscience, 5(1), pp.34~44 (1993)
- Chen, X., "Joint learning of character and word embeddings", Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)
- Collins, A. M., "A spreading-activation theory of semantic processing", Psychological review, 82(6), pp.407~ (1975)
- Deacon, D., "Event-related potential indices of semantic priming using masked and unmasked words : evidence that the n400 does not reflect a post-lexical process", Cognitive Brain Research, 9(2), pp.137~146 (2000)
- Ettinger, A., "Modeling n400 amplitude using vector space models of word representation", CogSci (2016)
- Federmeier, K. D., "A rose by any other name : Long-term memory structure and sentence processing", Journal of memory and Language, 41(4), pp.469~495 (1999)
- Firth, J. R., "A synopsis of linguistic theory, 1930-1955", Studies in linguistic analysis, pp.10~32 (1957)
- Hagoort, P., "Integration of word meaning and world knowledge in language comprehension", Science, 304(5669), pp.438~441 (2004)
- Harris, Z. S., "Distributional structure", Word, 10(2-3), pp.146~162 (1954)
- Holcomb, P. J., "Semantic priming and stimulus degradation : Implications for the role of the n400 in language processing", Psychophysiology, 30(1), pp.47~61 (1993)
- Huth, A. G., "Natural speech reveals the semantic maps that tile human cerebral cortex", Nature, 532(7600), pp.453~458 (2016)
- Khaligh-Razavi, S. -M., "Deep supervised, but not unsupervised, models may explain IT cortical representation", PLoS computational biology, 10(11), pp.e1003915~ (2014)
- Kiefer, M., "The n400 is modulated by unconsciously perceived masked words : Further evidence for an automatic spreading activation account of n400 priming effects", Cognitive Brain Research, 13(1), pp.27~39 (2002)
- Kriegeskorte, N., "Representational geometry : Integrating cognition, computation, and the brain", Trends in cognitive sciences, 17(8), pp.401~412 (2013)
- Kutas, M., "Thirty years and counting : finding meaning in the N400 component of the event-related brain potential(ERP)", Annual review of psychology, 62, pp.621~647 (2011)
- Kutas, M., "An electrophysiological probe of incidental semantic association", Journal of Cognitive Neuroscience, 1(1), pp.38~49 (1989)
- Lehmann, D., "Reference-free identification of components of checkerboard-evoked multichannel potential fields", Electroencephalography and Clinical Neurophysiology, 48(6), pp.609~621 (1980)
- Lin, D., "An information-theoretic definition of similarity", ICML, 98(1998), pp.296~304 (1998)
- Lorch Jr, R. F., "Priming and search processes in semantic memory : A test of three models of spreading activation", Journal of verbal learning and verbal behavior, 21(4), pp.468~492 (1982)
- Mikolov, T., "Efficient estimation of word representations in vector space" (2013)
- Miller, G. A., "Dictionaries in the mind", Language and cognitive processes, 1(3), pp.171~185 (1986)
- Neely, J. H., "Semantic priming and retrieval from lexical memory : Evidence for facilitatory and inhibitory processes", Memory & Cognition, 4(5), pp.648~654 (1976)
- Neely, J. H., "Semantic priming and retrieval from lexical memory : Roles of inhibitionless spreading activation and limited-capacity attention", Journal of experimental psychology : general, 106(3), pp.226~ (1977)
- Pennington, J., "GloVe: Global vectors for word representation", Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp.1532~1543 (2014)
- Poeppel, D., "The maps problem and the mapping problem: two challenges for a cognitive neuroscience of speech and language", Cognitive neuropsychology, 29(1-2), pp.34~55 (2012)
- Pylkkänen, L., "The neural basis of combinatory syntax and semantics", Science, 366(6461), pp.62~66 (2019)
- Resnik, P., "Using information content to evaluate semantic similarity in a taxonomy" (1995)
- Resnik, P., "Semantic similarity in a taxonomy : An information-based measure and its application to problems of ambiguity in natural language", Journal of Artificial Intelligence Research, 11, pp.95~130 (1999)
- Roelofs, A., "A spreading-activation theory of lemma retrieval in speaking", Cognition, 42(1-3), pp.107~142 (1992)
- Turney, P. D., "From frequency to meaning : Vector space models of semantics", Journal of Artificial Intelligence Research, 37, pp.141~188 (2010)
- Wang, X., "Revealing the temporal dynamics in non-invasive electrophysiological recordings with topography-based analyses" (2019)[DOI]
- Yamins, D., "Performance-optimized hierarchical models predict neural responses in higher visual cortex", Proceedings of the National Academy of Sciences, 111(23), pp.8619~8624 (2014)
- Yang, J., "Group-level multivariate analysis in EasyEEG toolbox : Examining the temporal dynamics using topographic responses", Frontiers in Neuroscience, 12, pp.468~ (2018)
- Zhang, L., "The interplay of composition and concept specificity in the left anterior temporal lobe : An meg study", NeuroImage, 111, pp.228~240 (2015)