Humans are sensitive to the properties of individual items, and exemplar models are useful for capturing this sensitivity. I am a proponent of an extension of exemplar-based architectures that I briefly describe. However, exemplar models are very shallow architectures in which it is necessary to stipulate a set of primitive elements that make up each example, and such architectures have not been as successful as deep neural networks in capturing language usage and meaning. More work is needed bringing contemporary deep learning architectures used in machine intelligence to the effort to understand human language processing.
AmbridgeB. (2020). Against stored abstractions: A radical exemplar model of language acquisition. First Language40(5-6): 509–559.
2.
KrizhevskyA.SutskeverI.HintonG. E. (2012). ImageNet classification with deep convolutional neural networks. In PereiraF.BurgesC. J. C.BottouL. (Eds.), Advances in neural information processing systems (pp. 1097–1105). Neural Information Processing Systems Foundation, Inc.
3.
KumaranD.McClellandJ. L. (2012). Generalization through the recurrent interaction of episodic memories: A model of the hippocampal system. Psychological Review, 119, 573–616.
4.
McClellandJ. L. (1981). Retrieving general and specific information from stored knowledge of specifics. In Proceedings of the Third Annual Conference of the Cognitive Science Society (pp. 170–172). Cognitive Science Society.
5.
McClellandJ. L. (2016). Capturing gradience, continuous change, and quasi-regularity in sound, word, phrase, and meaning. In MacWhinneyB.O’GradyW. (Eds.), The handbook of language emergence (pp. 54–80). John Wiley & Sons.
6.
McClellandJ. L.HillF.RudolphM.BaldridgeJ.ShuetzeH. (2019). Extending machine language models toward human-level language understanding. arXiv: 1912.05877.
7.
McClellandJ. L.RumelhartD. E. (1981). An interactive activation model of context effects in letter perception: Part 1. An account of basic findings. Psychological Review, 88, 375–407.
8.
McClellandJ. L.RumelhartD. E. (1986). A distributed model of memory. In McClellandJ. L.RumelhartD. E., & The PDP Research Group. (Eds.), Parallel distributed processing: Explorations in the microstructure of cognition, Volume II (pp. 170–215). MIT Press.
9.
MedinD. L.SchafferM. M. (1978). Context theory of classification learning. Psychological Review, 85(3), 207–238.
10.
RaffelC.ShazeerN.RobertsA.LeeK.NarangS.MatenaM.ZhouY.LiW.LiuP. J. (2019). Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:191010683.
11.
RumelhartD. E.McClellandJ. L. (1986). On learning the past tenses of English verbs. In McClellandJ. L.RumelhartD. E., & The PDP Research Group. (Eds.), Parallel distributed processing: Explorations in the microstructure of cognition. Volume II (pp. 216–271). MIT Press.
12.
YaminsD. L.HongH.CadieuC. F.SolomonE. A.SeibertD.DiCarloJ. J. (2014). Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proceedings of the National Academy of Sciences of the United States of America, 111(23), 8619–8624.
