{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T08:44:43Z","timestamp":1782377083364,"version":"3.54.5"},"publisher-location":"Cham","reference-count":93,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031053108","type":"print"},{"value":"9783031053115","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-05311-5_9","type":"book-chapter","created":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T19:04:19Z","timestamp":1655319859000},"page":"137-160","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Semantics for\u00a0Affordances and\u00a0Actions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2233-9761","authenticated-orcid":false,"given":"James","family":"Pustejovsky","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-7227","authenticated-orcid":false,"given":"Nikhil","family":"Krishnaswamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,6,16]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Alikhani, M., Khalid, B., Shome, R., Mitash, C., Bekris, K., Stone, M.: That and there: judging the intent of pointing actions with robotic arms. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10343\u201310351 (2020)","DOI":"10.1609\/aaai.v34i06.6601"},{"issue":"1","key":"9_CR2","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/S0004-3702(03)00054-7","volume":"149","author":"ML Anderson","year":"2003","unstructured":"Anderson, M.L.: Embodied cognition: a field guide. Artif. Intell. 149(1), 91\u2013130 (2003)","journal-title":"Artif. Intell."},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"9_CR4","unstructured":"Asher, N.: Common ground, corrections and coordination. J. Semant. (1998)"},{"key":"9_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-642-25655-4_2","volume-title":"New Frontiers in Artificial Intelligence","author":"N Asher","year":"2011","unstructured":"Asher, N., Pogodalla, S.: SDRT and continuation semantics. In: Onada, T., Bekki, D., McCready, E. (eds.) JSAI-ISAI 2010. LNCS (LNAI), vol. 6797, pp. 3\u201315. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-25655-4_2"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Barker, C., Shan, C.C.: Continuations and natural language. Oxford Studies in Theoretical Linguistics, vol. 53 (2014)","DOI":"10.1093\/acprof:oso\/9780199575015.001.0001"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Beniaguev, D., Segev, I., London, M.: Single cortical neurons as deep artificial neural networks. bioRxiv p. 613141 (2020)","DOI":"10.2139\/ssrn.3717773"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Blackburn, P., Bos, J.: Computational semantics. Theoria: Int. J. Theory Hist. Found. Sci. 27\u201345 (2003)","DOI":"10.1387\/theoria.408"},{"issue":"1\u20133","key":"9_CR9","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/0004-3702(91)90053-M","volume":"47","author":"RA Brooks","year":"1991","unstructured":"Brooks, R.A.: Intelligence without representation. Artif. Intell. 47(1\u20133), 139\u2013159 (1991)","journal-title":"Artif. Intell."},{"key":"9_CR10","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"9_CR11","unstructured":"Caligiore, D., Ferrauto, T., Parisi, D., Accornero, N., Capozza, M., Baldassarre, G.: Using motor babbling and Hebb rules for modeling the development of reaching with obstacles and grasping. In: International Conference on Cognitive Systems, pp. E1\u2013E8 (2008)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Cassell, J., Sullivan, J., Churchill, E., Prevost, S.: Embodied Conversational Agents. MIT Press (2000)","DOI":"10.7551\/mitpress\/2697.001.0001"},{"issue":"4","key":"9_CR13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1609\/aimag.v37i4.2684","volume":"37","author":"JY Chai","year":"2016","unstructured":"Chai, J.Y., Fang, R., Liu, C., She, L.: Collaborative language grounding toward situated human-robot dialogue. AI Magazine 37(4), 32\u201345 (2016)","journal-title":"AI Magazine"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 381\u2013389. IEEE (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"9_CR15","unstructured":"Chemero, A.: Radical Embodied Cognitive Science. MIT Press (2011)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Chen, C., Seff, A., Kornhauser, A., Xiao, J.: Deepdriving: learning affordance for direct perception in autonomous driving. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2722\u20132730 (2015)","DOI":"10.1109\/ICCV.2015.312"},{"issue":"1","key":"9_CR17","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/S0004-3702(03)00055-9","volume":"149","author":"R Chrisley","year":"2003","unstructured":"Chrisley, R.: Embodied artificial intelligence. Artif. Intell. 149(1), 131\u2013150 (2003)","journal-title":"Artif. Intell."},{"issue":"8","key":"9_CR18","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.tics.2006.06.012","volume":"10","author":"A Clark","year":"2006","unstructured":"Clark, A.: Language, embodiment, and the cognitive niche. Trends Cognit. Sci. 10(8), 370\u2013374 (2006)","journal-title":"Trends Cognit. Sci."},{"issue":"1991","key":"9_CR19","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1037\/10096-006","volume":"13","author":"HH Clark","year":"1991","unstructured":"Clark, H.H., Brennan, S.E.: Grounding in communication. Perspect. Social. Shared Cognit. 13(1991), 127\u2013149 (1991)","journal-title":"Perspect. Social. Shared Cognit."},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Colung, E., Smith, L.B.: The emergence of abstract ideas: evidence from networks and babies. Philos. Trans. Roy. Soc. London Ser. B Biol. Sci. 358(1435), 1205\u20131214 (2003)","DOI":"10.1098\/rstb.2003.1306"},{"key":"9_CR21","unstructured":"Coventry, K., Garrod, S.C.: Spatial prepositions and the functional geometric framework. In: Towards a Classification of Extra-Geometric Influences (2005)"},{"key":"9_CR22","unstructured":"De Groote, P.: Type raising, continuations, and classical logic. In: Proceedings of the Thirteenth Amsterdam Colloquium, pp. 97\u2013101 (2001)"},{"issue":"2","key":"9_CR23","first-page":"273","volume":"5","author":"S Dobnik","year":"2017","unstructured":"Dobnik, S., Cooper, R.: Interfacing language, spatial perception and cognition in type theory with records. J. Lang. Model. 5(2), 273\u2013301 (2017)","journal-title":"J. Lang. Model."},{"issue":"4","key":"9_CR24","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1609\/aimag.v32i4.2377","volume":"32","author":"K Fischer","year":"2011","unstructured":"Fischer, K.: How people talk with robots: designing dialog to reduce user uncertainty. AI Magazine 32(4), 31\u201338 (2011)","journal-title":"AI Magazine"},{"key":"9_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1007\/978-3-540-73281-5_91","volume-title":"Universal Access in Human-Computer Interaction. Ambient Interaction","author":"ME Foster","year":"2007","unstructured":"Foster, M.E.: Enhancing human-computer interaction with embodied conversational agents. In: Stephanidis, C. (ed.) UAHCI 2007. LNCS, vol. 4555, pp. 828\u2013837. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-73281-5_91"},{"key":"9_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/3-540-55966-3_10","volume-title":"Theories and Methods of Spatio-Temporal Reasoning in Geographic Space","author":"C Freksa","year":"1992","unstructured":"Freksa, C.: Using orientation information for qualitative spatial reasoning. In: Frank, A.U., Campari, I., Formentini, U. (eds.) GIS 1992. LNCS, vol. 639, pp. 162\u2013178. Springer, Heidelberg (1992). https:\/\/doi.org\/10.1007\/3-540-55966-3_10"},{"key":"9_CR27","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"9_CR28","unstructured":"Gibson, J.J.: The theory of affordances. In: Perceiving, Acting, and Knowing: Toward an Ecological Psychology, pp. 67\u201382 (1977)"},{"key":"9_CR29","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception. Psychology Press (1979)"},{"key":"9_CR30","unstructured":"Ginzburg, J.: Interrogatives: questions, facts and dialogue. The Handbook of Contemporary Semantic Theory, pp. 359\u2013423. Blackwell, Oxford (1996)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8359\u20138367 (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"issue":"1","key":"9_CR32","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1038\/scientificamerican0710-76","volume":"303","author":"A Gopnik","year":"2010","unstructured":"Gopnik, A.: How babies think. Sci. Am. 303(1), 76\u201381 (2010)","journal-title":"Sci. Am."},{"issue":"12","key":"9_CR33","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1038\/s41583-018-0078-0","volume":"19","author":"J Gottlieb","year":"2018","unstructured":"Gottlieb, J., Oudeyer, P.Y.: Towards a neuroscience of active sampling and curiosity. Nat. Rev. Neurosci. 19(12), 758\u2013770 (2018)","journal-title":"Nat. Rev. Neurosci."},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Hunter, J., Asher, N., Lascarides, A.: A formal semantics for situated conversation. Semant. Pragmat. 11 (2018)","DOI":"10.3765\/sp.11.10"},{"key":"9_CR35","unstructured":"Kayhan, O.S., Gemert, J.C.V.: On translation invariance in CNNs: convolutional layers can exploit absolute spatial location. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14274\u201314285 (2020)"},{"key":"9_CR36","unstructured":"Kennington, C., Kousidis, S., Schlangen, D.: Interpreting situated dialogue utterances: an update model that uses speech, gaze, and gesture information. In: Proceedings of SigDial 2013 (2013)"},{"key":"9_CR37","unstructured":"Kiela, D., Bulat, L., Vero, A.L., Clark, S.: Virtual embodiment: a scalable long-term strategy for artificial intelligence research. arXiv preprint arXiv:1610.07432 (2016)"},{"key":"9_CR38","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"7","key":"9_CR39","doi-asserted-by":"publisher","first-page":"3985","DOI":"10.1523\/JNEUROSCI.14-07-03985.1994","volume":"14","author":"EI Knudsen","year":"1994","unstructured":"Knudsen, E.I.: Supervised learning in the brain. J. Neurosci. 14(7), 3985\u20133997 (1994)","journal-title":"J. Neurosci."},{"key":"9_CR40","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-540-24640-4_4","volume-title":"Model Generation for Natural Language Interpretation and Analysis","author":"Karsten Konrad","year":"2004","unstructured":"Konrad, Karsten: 4 Minimal model generation. In: Model Generation for Natural Language Interpretation and Analysis. LNCS (LNAI), vol. 2953, pp. 55\u201356. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24640-4_4"},{"key":"9_CR41","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12553-9","volume-title":"Gesture in Embodied Communication and Human-Computer Interaction","year":"2010","unstructured":"Kopp, S., Wachsmuth, I. (eds.): GW 2009. LNCS (LNAI), vol. 5934. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12553-9"},{"key":"9_CR42","unstructured":"Krishnaswamy, N.: Monte-Carlo simulation generation through operationalization of spatial primitives. Ph.D. thesis, Brandeis University (2017)"},{"key":"9_CR43","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-319-68189-4_11","volume-title":"Spatial Cognition X","author":"N Krishnaswamy","year":"2017","unstructured":"Krishnaswamy, N., Pustejovsky, J.: Multimodal semantic simulations of linguistically underspecified motion events. In: Barkowsky, T., Burte, H., H\u00f6lscher, C., Schultheis, H. (eds.) Spatial Cognition\/KogWis -2016. LNCS (LNAI), vol. 10523, pp. 177\u2013197. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68189-4_11"},{"key":"9_CR44","unstructured":"Krishnaswamy, N., Pustejovsky, J.: VoxSim: a visual platform for modeling motion language. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics. ACL (2016)"},{"key":"9_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1007\/978-3-030-77817-0_17","volume-title":"Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Human Body, Motion and Behavior","author":"N Krishnaswamy","year":"2021","unstructured":"Krishnaswamy, N., Pustejovsky, J.: The role of embodiment and simulation in evaluating HCI: experiments and evaluation. In: Duffy, V.G. (ed.) HCII 2021. LNCS, vol. 12777, pp. 220\u2013232. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-77817-0_17"},{"key":"9_CR46","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"9_CR47","doi-asserted-by":"crossref","unstructured":"Kruijff, G.J.M., et al.: Situated dialogue processing for human-robot interaction. In: Cognitive Systems, pp. 311\u2013364. Springer, Heidelberg (2010)","DOI":"10.1007\/978-3-642-11694-0_8"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Lakoff, G.: The invariance hypothesis: is abstract reason based on image-schemas? (1990)","DOI":"10.1515\/cogl.1990.1.1.39"},{"issue":"12","key":"9_CR49","doi-asserted-by":"publisher","first-page":"3578","DOI":"10.1016\/j.sigpro.2006.02.046","volume":"86","author":"F Landragin","year":"2006","unstructured":"Landragin, F.: Visual perception, language and gesture: a model for their understanding in multimodal dialogue systems. Signal Process. 86(12), 3578\u20133595 (2006)","journal-title":"Signal Process."},{"key":"9_CR50","unstructured":"Larsson, S., Ericsson, S.: Godis-issue-based dialogue management in a multi-domain, multi-language dialogue system. In: Demonstration Abstracts, ACL-02 (2002)"},{"key":"9_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/978-3-319-46475-6_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Lin","year":"2016","unstructured":"Lin, X., Parikh, D.: Leveraging visual question answering for image-caption ranking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 261\u2013277. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_17"},{"issue":"1","key":"9_CR52","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1037\/a0032108","volume":"143","author":"DB Markant","year":"2014","unstructured":"Markant, D.B., Gureckis, T.M.: Is it better to select or to receive? learning via active and passive hypothesis testing. J. Exp. Psychol. Gen. 143(1), 94 (2014)","journal-title":"J. Exp. Psychol. Gen."},{"key":"9_CR53","doi-asserted-by":"publisher","first-page":"144","DOI":"10.4135\/9781446282229.n11","volume":"1","author":"P Marshall","year":"2013","unstructured":"Marshall, P., Hornecker, E.: Theories of embodiment in HCI. SAGE Handb. Digit. Technol. Res. 1, 144\u2013158 (2013)","journal-title":"SAGE Handb. Digit. Technol. Res."},{"key":"9_CR54","doi-asserted-by":"crossref","unstructured":"Misra, D., Langford, J., Artzi, Y.: Mapping instructions and visual observations to actions with reinforcement learning. arXiv preprint arXiv:1704.08795 (2017)","DOI":"10.18653\/v1\/D17-1106"},{"key":"9_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/3-540-45004-1_22","volume-title":"Spatial Cognition III","author":"R Moratz","year":"2003","unstructured":"Moratz, R., Nebel, B., Freksa, C.: Qualitative spatial reasoning about relative position. In: Freksa, C., Brauer, W., Habel, C., Wender, K.F. (eds.) Spatial Cognition 2002. LNCS, vol. 2685, pp. 385\u2013400. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45004-1_22"},{"issue":"1","key":"9_CR56","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1207\/s15427633scc0601_3","volume":"6","author":"R Moratz","year":"2006","unstructured":"Moratz, R., Tenbrink, T.: Spatial reference in linguistic human-robot interaction: iterative, empirically supported development of a model of projective relations. Spatial Cognit. Comput. 6(1), 63\u2013107 (2006)","journal-title":"Spatial Cognit. Comput."},{"key":"9_CR57","doi-asserted-by":"crossref","unstructured":"Muller, P., Pr\u00e9vot, L.: Grounding information in route explanation dialogues (2009)","DOI":"10.1093\/acprof:oso\/9780199554201.003.0012"},{"issue":"3","key":"9_CR58","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/8.3.4","volume":"8","author":"J Najemnik","year":"2008","unstructured":"Najemnik, J., Geisler, W.S.: Eye movement statistics in humans are consistent with an optimal search strategy. J. Vis. 8(3), 4\u20134 (2008)","journal-title":"J. Vis."},{"issue":"3","key":"9_CR59","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1038\/s42256-019-0025-4","volume":"1","author":"EO Neftci","year":"2019","unstructured":"Neftci, E.O., Averbeck, B.B.: Reinforcement learning in artificial and biological systems. Nat. Mach. Intell. 1(3), 133\u2013143 (2019)","journal-title":"Nat. Mach. Intell."},{"issue":"7","key":"9_CR60","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1177\/0956797610372637","volume":"21","author":"JD Nelson","year":"2010","unstructured":"Nelson, J.D., McKenzie, C.R., Cottrell, G.W., Sejnowski, T.J.: Experience matters: information acquisition optimizes probability gain. Psychol. Sci. 21(7), 960\u2013969 (2010)","journal-title":"Psychol. Sci."},{"issue":"3","key":"9_CR61","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.jmp.2008.12.005","volume":"53","author":"Y Niv","year":"2009","unstructured":"Niv, Y.: Reinforcement learning in the brain. J. Math. Psychol. 53(3), 139\u2013154 (2009)","journal-title":"J. Math. Psychol."},{"key":"9_CR62","unstructured":"Piaget, J.: The attainment of invariants and reversible operations in the development of thinking. Soc. Res. 283\u2013299 (1963)"},{"key":"9_CR63","unstructured":"Piaget, J., Inhelder, B.: The Psychology of the Child. Basic Books (1962)"},{"key":"9_CR64","doi-asserted-by":"crossref","unstructured":"Pustejovsky, J.: The Generative Lexicon. MIT Press (1995)","DOI":"10.7551\/mitpress\/3225.001.0001"},{"key":"9_CR65","unstructured":"Pustejovsky, J.: Dynamic event structure and habitat theory. In: Proceedings of the 6th International Conference on Generative Approaches to the Lexicon (GL2013), pp. 1\u201310. ACL (2013)"},{"key":"9_CR66","unstructured":"Pustejovsky, J.: Affordances and the functional characterization of space. In: Cognitive Processing, vol. 16, p. S43. Springer, Heidelberg (2015)"},{"key":"9_CR67","unstructured":"Pustejovsky, J.: Computational models of events. In: ESSLLI Summer School, August 2018, Sofia, Bulgaria (2018)"},{"issue":"1\u20132","key":"9_CR68","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/0004-3702(93)90017-6","volume":"63","author":"J Pustejovsky","year":"1993","unstructured":"Pustejovsky, J., Boguraev, B.: Lexical knowledge representation and natural language processing. Artif. Intell. 63(1\u20132), 193\u2013223 (1993)","journal-title":"Artif. Intell."},{"key":"9_CR69","doi-asserted-by":"crossref","unstructured":"Pustejovsky, J., Krishnaswamy, N.: Voxml: a visualization modeling language. In: Proceedings of LREC (2016)","DOI":"10.63317\/4iaxfpeztyaf"},{"issue":"3","key":"9_CR70","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s13218-021-00727-5","volume":"35","author":"J Pustejovsky","year":"2021","unstructured":"Pustejovsky, J., Krishnaswamy, N.: Embodied human computer interaction. KI-K\u00fcnstliche Intell. 35(3), 307\u2013327 (2021)","journal-title":"KI-K\u00fcnstliche Intell."},{"key":"9_CR71","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/978-3-030-77817-0_21","volume-title":"Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Human Body, Motion and Behavior","author":"J Pustejovsky","year":"2021","unstructured":"Pustejovsky, J., Krishnaswamy, N.: The role of embodiment and simulation in evaluating HCI: theory and\u00a0framework. In: Duffy, V.G. (ed.) HCII 2021. LNCS, vol. 12777, pp. 288\u2013303. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-77817-0_21"},{"issue":"1","key":"9_CR72","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1080\/13875868.2010.543497","volume":"11","author":"J Pustejovsky","year":"2011","unstructured":"Pustejovsky, J., Moszkowicz, J.L.: The qualitative spatial dynamics of motion in language. Spatial Cognit. Comput. 11(1), 15\u201344 (2011)","journal-title":"Spatial Cognit. Comput."},{"key":"9_CR73","doi-asserted-by":"crossref","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.C.: Learning human-object interactions by graph parsing neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 401\u2013417 (2018)","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"9_CR74","unstructured":"Randell, D., Cui, Z., Cohn, A., Nebel, B., Rich, C., Swartout, W.: A spatial logic based on regions and connection. In: Proceedings of the 3rd International Conference on Principles of Knowledge Representation and Reasoning (KR 1992), pp. 165\u2013176. Morgan Kaufmann, San Mateo (1992)"},{"key":"9_CR75","doi-asserted-by":"publisher","unstructured":"Renninger, L.W., Verghese, P., Coughlan, J.: Where to look next? eye movements reduce local uncertainty. J. Vis. 7(3) (2007). https:\/\/doi.org\/10.1167\/7.3.6","DOI":"10.1167\/7.3.6"},{"key":"9_CR76","doi-asserted-by":"crossref","unstructured":"Schaffer, S., Reithinger, N.: Conversation is multimodal: thus conversational user interfaces should be as well. In: Proceedings of the 1st International Conference on Conversational User Interfaces, pp. 1\u20133 (2019)","DOI":"10.1145\/3342775.3342801"},{"issue":"4","key":"9_CR77","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1609\/aimag.v32i4.2381","volume":"32","author":"M Scheutz","year":"2011","unstructured":"Scheutz, M., Cantrell, R., Schermerhorn, P.: Toward humanlike task-based dialogue processing for human robot interaction. Ai Magazine 32(4), 77\u201384 (2011)","journal-title":"Ai Magazine"},{"key":"9_CR78","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: It\u2019s not just size that matters: small language models are also few-shot learners. arXiv preprint arXiv:2009.07118 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"issue":"3","key":"9_CR79","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s10988-017-9225-8","volume":"41","author":"P Schlenker","year":"2018","unstructured":"Schlenker, P.: Gesture projection and cosuppositions. Linguist. Philos. 41(3), 295\u2013365 (2018)","journal-title":"Linguist. Philos."},{"issue":"4","key":"9_CR80","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1037\/0012-1649.43.4.1045","volume":"43","author":"LE Schulz","year":"2007","unstructured":"Schulz, L.E., Bonawitz, E.B.: Serious fun: preschoolers engage in more exploratory play when evidence is confounded. Develop. Psychol. 43(4), 1045 (2007)","journal-title":"Develop. Psychol."},{"key":"9_CR81","doi-asserted-by":"crossref","unstructured":"Shapiro, L.: Embodied Cognition. Routledge, London (2010)","DOI":"10.4324\/9780203850664"},{"key":"9_CR82","doi-asserted-by":"crossref","unstructured":"Shapiro, L.A.: The Routledge Handbook of Embodied Cognition (2014)","DOI":"10.4324\/9781315775845"},{"issue":"4","key":"9_CR83","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1207\/s15516709cog0000_74","volume":"30","author":"LK Son","year":"2006","unstructured":"Son, L.K., Sethi, R.: Metacognitive control and optimal learning. Cognit. Sci. 30(4), 759\u2013774 (2006)","journal-title":"Cognit. Sci."},{"issue":"5\u20136","key":"9_CR84","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1023\/A:1020867916902","volume":"25","author":"R Stalnaker","year":"2002","unstructured":"Stalnaker, R.: Common ground. Linguist. Philos. 25(5\u20136), 701\u2013721 (2002)","journal-title":"Linguist. Philos."},{"key":"9_CR85","doi-asserted-by":"crossref","unstructured":"Stojni\u0107, U., Stone, M., Lepore, E.: Pointing things out: in defense of attention and coherence. Linguist. Philos. 1\u201310 (2019)","DOI":"10.1007\/s10988-019-09271-w"},{"issue":"1","key":"9_CR86","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1111\/j.1467-7687.2007.00573.x","volume":"10","author":"M Tomasello","year":"2007","unstructured":"Tomasello, M., Carpenter, M.: Shared intentionality. Develop. Sci. 10(1), 121\u2013125 (2007)","journal-title":"Develop. Sci."},{"key":"9_CR87","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3389\/fpsyg.2012.00046","volume":"3","author":"H Vlach","year":"2012","unstructured":"Vlach, H., Sandhofer, C.M.: Fast mapping across time: memory processes support children\u2019s retention of learned words. Front. Psychol. 3, 46 (2012)","journal-title":"Front. Psychol."},{"key":"9_CR88","doi-asserted-by":"publisher","unstructured":"Wahlster, W.: Dialogue systems go multimodal: the Smartkom experience. In: SmartKom: Foundations of Multimodal Dialogue Systems, pp. 3\u201327. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/3-540-36678-4_1","DOI":"10.1007\/3-540-36678-4_1"},{"issue":"1","key":"9_CR89","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/S1364-6613(98)01261-3","volume":"3","author":"G Wallis","year":"1999","unstructured":"Wallis, G., B\u00fclthoff, H.: Learning to recognize objects. Trends Cognit. Sci. 3(1), 22\u201331 (1999)","journal-title":"Trends Cognit. Sci."},{"key":"9_CR90","doi-asserted-by":"publisher","first-page":"58","DOI":"10.3389\/fpsyg.2013.00058","volume":"4","author":"AD Wilson","year":"2013","unstructured":"Wilson, A.D., Golonka, S.: Embodied cognition is not what you think it is. Front. Psychol. 4, 58 (2013)","journal-title":"Front. Psychol."},{"key":"9_CR91","doi-asserted-by":"crossref","unstructured":"Xu, B., Wong, Y., Li, J., Zhao, Q., Kankanhalli, M.S.: Learning to detect human-object interactions with knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00212"},{"key":"9_CR92","doi-asserted-by":"crossref","unstructured":"Yatskar, M., Zettlemoyer, L., Farhadi, A.: Situation recognition: visual semantic role labeling for image understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5534\u20135542 (2016)","DOI":"10.1109\/CVPR.2016.597"},{"issue":"1","key":"9_CR93","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-019-11786-6","volume":"10","author":"AM Zador","year":"2019","unstructured":"Zador, A.M.: A critique of pure learning and what artificial neural networks can learn from animal brains. Nat. Commun. 10(1), 1\u20137 (2019)","journal-title":"Nat. Commun."}],"container-title":["Lecture Notes in Computer Science","Human-Computer Interaction. Theoretical Approaches and Design Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-05311-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:47:53Z","timestamp":1781570873000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-05311-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031053108","9783031053115"],"references-count":93,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-05311-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.hci.international\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}