{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T11:32:17Z","timestamp":1753875137676,"version":"3.41.2"},"reference-count":41,"publisher":"Informa UK Limited","issue":"1","license":[{"start":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T00:00:00Z","timestamp":1677024000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Research Foundation (DFG) under Project TRR 169 Crossmodal Learning (CML), LeCareBot, IDEAS, and MoReSpace"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Applied Artificial Intelligence"],"published-print":{"date-parts":[[2023,12,31]]},"DOI":"10.1080\/08839514.2023.2179167","type":"journal-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T13:48:26Z","timestamp":1677073706000},"update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":1,"title":["Learning Bidirectional Action-Language Translation with Limited Supervision and Testing with Incongruent Input"],"prefix":"10.1080","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2410-5192","authenticated-orcid":false,"given":"Ozan","family":"\u00d6zdemir","sequence":"first","affiliation":[{"name":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Kerzel","sequence":"additional","affiliation":[{"name":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[{"name":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae Hee","family":"Lee","sequence":"additional","affiliation":[{"name":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Burhan","family":"Hafez","sequence":"additional","affiliation":[{"name":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Bruns","sequence":"additional","affiliation":[{"name":"Biological Psychology and Neuropsychology, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2023,2,22]]},"reference":[{"key":"e_1_3_3_2_1","first-page":"1","article-title":"Imitating interactive intelligence","volume":"2012","author":"Abramson J.","year":"2020","unstructured":"Abramson, J., A. Ahuja, A. Brussee, F. Carnevale, M. Cassin, S. Clark, A. Dudzik, P. Georgiev, A. Guy, T. Harley, et al. 2020. Imitating interactive intelligence. arXiv preprint arXiv: 201205672 abs\/2012.05672:1\u2013768.","journal-title":"arXiv preprint arXiv: 201205672"},{"key":"e_1_3_3_3_1","first-page":"1","article-title":"Do as I can and not as I say: Grounding language in robotic affordances","volume":"2204","author":"Ahn M.","year":"2022","unstructured":"Ahn, M., A. Brohan, N. Brown, Y. Chebotar, O. Cortes, B. David, C. Finn, C. Fu, K. Gopalakrishnan, K. Hausman, et al. 2022. Do as I can and not as I say: Grounding language in robotic affordances. arXiv preprint arXiv: 220401691 abs\/2204.01691:1\u201334.","journal-title":"arXiv preprint arXiv: 220401691"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967799"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0011751"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04559-1"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.703"},{"key":"e_1_3_3_8_1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown T.","year":"2020","unstructured":"Brown, T., B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33:1877\u2013901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0958344022000118"},{"key":"e_1_3_3_10_1","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin J.","year":"2019","unstructured":"Devlin, J., M.-W. Chang, K. Lee, and K. Toutanova. 2019, June. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, Minnesota, pp. 4171\u201386. Association for Computational Linguistics."},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534275"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03196313"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(03)00838-9"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.00052"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561806"},{"key":"e_1_3_3_18_1","volume-title":"International Conference on Learning Representations","author":"Jaegle A.","year":"2022","unstructured":"Jaegle, A., S. Borgeaud, J.-B. Alayrac, C. Doersch, C. Ionescu, D. Ding, S. Koppula, D. Zoran, A. Brock, E. Shelhamer, et al. 2022. Perceiver io: A general architecture for structured inputs & outputs. In International Conference on Learning Representations, Virtual."},{"key":"e_1_3_3_19_1","volume-title":"5th Annual Conference on Robot Learning","author":"Jang E.","year":"2021","unstructured":"Jang, E., A. Irpan, M. Khansari, D. Kappler, F. Ebert, C. Lynch, S. Levine, and C. Finn. 2021. BC-z: Zero-shot task generalization with robotic imitation learning. In 5th Annual Conference on Robot Learning, London, UK."},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2004.06.005"},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.00028"},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2017.8172289"},{"key":"e_1_3_3_24_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Kingma D. P.","year":"2015","unstructured":"Kingma, D. P., and J. Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR, San Diego, CA, USA, May 7-9."},{"key":"e_1_3_3_25_1","first-page":"13","volume-title":"Advances in neural information processing systems","author":"Lu J.","year":"2019","unstructured":"Lu, J., D. Batra, D. Parikh, and S. Lee. 2019. ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In Advances in neural information processing systems, ed. H. Wallach, H. Larochelle, A. Beygelzimer, F. D Alch\u00e9-Buc, E. Fox, and R. Garnett, vol. 32, 13\u201323. New York, US: Curran Associates, Inc."},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.047"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2007.02016.x"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399265"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15931-2_21"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDL49984.2021.9515668"},{"key":"e_1_3_3_31_1","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford A.","year":"2021","unstructured":"Radford, A., J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, Virtual, pp. 8748\u201363. PMLR."},{"key":"e_1_3_3_32_1","unstructured":"Radford A. J. Wu R. Child D. Luan D. Amodei and I. Sutskever. 2019. Language models are unsupervised multitask learners."},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1214\/10-BA521"},{"key":"e_1_3_3_34_1","first-page":"1","article-title":"A generalist agent","volume":"11","author":"Reed S.","year":"2022","unstructured":"Reed, S., K. Zolna, E. Parisotto, S. G. Colmenarejo, A. Novikov, G. Barth-Maron, M. Gimenez, Y. Sulsky, J. Kay, J. T. Springenberg, et al. 2022. A generalist agent. Transactions on Machine Learning Research 11\/2022:1\u201342 .","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.082"},{"key":"e_1_3_3_36_1","volume-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)","author":"Shridhar M.","year":"2021","unstructured":"Shridhar, M., L. Manuelli, and D. Fox. 2021. Cliport: What and where pathways for robotic manipulation. In Proceedings of the 5th Conference on Robot Learning (CoRL), London, UK."},{"key":"e_1_3_3_37_1","volume-title":"Proceedings of the 6th Conference on Robot Learning (CoRL)","author":"Shridhar M.","year":"2022","unstructured":"Shridhar, M., L. Manuelli, and D. Fox. 2022. Perceiver-Actor: A multi-task transformer for robotic manipulation. In Proceedings of the 6th Conference on Robot Learning (CoRL), Auckland, New Zealand."},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919897133"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2009.12.123"},{"key":"e_1_3_3_40_1","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani A.","year":"2017","unstructured":"Vaswani, A., N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, and I. Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30: 5998\u20136008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2022.103712"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852838"},{"key":"e_1_3_3_43_1","first-page":"726","volume-title":"4th Conference on Robot Learning, CoRL 2020, 16-18 November 2020, virtual Event\/Cambridge, MA, USA, Volume 155 of proceedings of Machine Learning Research","author":"Zeng A.","year":"2020","unstructured":"Zeng, A., P. Florence, J. Tompson, S. Welker, J. Chien, M. Attarian, T. Armstrong, I. Krasin, D. Duong, V. Sindhwani, et al. 2020. Transporter networks: Rearranging the visual world for robotic manipulation. In 4th Conference on Robot Learning, CoRL 2020, 16-18 November 2020, virtual Event\/Cambridge, MA, USA, Volume 155 of proceedings of Machine Learning Research, ed. J. Kober, F. Ramos, and C. J. Tomlin, 726\u201347. PMLR."}],"container-title":["Applied Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/08839514.2023.2179167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T09:13:19Z","timestamp":1712567599000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/08839514.2023.2179167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,22]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,12,31]]}},"alternative-id":["10.1080\/08839514.2023.2179167"],"URL":"https:\/\/doi.org\/10.1080\/08839514.2023.2179167","relation":{},"ISSN":["0883-9514","1087-6545"],"issn-type":[{"type":"print","value":"0883-9514"},{"type":"electronic","value":"1087-6545"}],"subject":[],"published":{"date-parts":[[2023,2,22]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=uaai20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=uaai20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2022-12-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-02","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2179167"}}