{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robots-learning-to-say-no-prohibition-and","title":"Robots Learning to Say `No': Prohibition and Rejective Mechanisms in Acquisition of Linguistic Negation","arxiv_id":"1810.11804","date":"2018-10-28","proceeding":null,"authors":["Frank Förster","Joe Saunders","Hagen Lehmann","Chrystopher L. Nehaniv"],"abstract":"`No' belongs to the first ten words used by children and embodies the first\nactive form of linguistic negation. Despite its early occurrence the details of\nits acquisition process remain largely unknown. The circumstance that `no'\ncannot be construed as a label for perceptible objects or events puts it\noutside of the scope of most modern accounts of language acquisition. Moreover,\nmost symbol grounding architectures will struggle to ground the word due to its\nnon-referential character. In an experimental study involving the child-like\nhumanoid robot iCub that was designed to illuminate the acquisition process of\nnegation words, the robot is deployed in several rounds of speech-wise\nunconstrained interaction with na\\\"ive participants acting as its language\nteachers. The results corroborate the hypothesis that affect or volition plays\na pivotal role in the socially distributed acquisition process. Negation words\nare prosodically salient within prohibitive utterances and negative intent\ninterpretations such that they can be easily isolated from the teacher's speech\nsignal. These words subsequently may be grounded in negative affective states.\nHowever, observations of the nature of prohibitive acts and the temporal\nrelationships between its linguistic and extra-linguistic components raise\nserious questions over the suitability of Hebbian-type algorithms for language\ngrounding.","url_abs":"http://arxiv.org/abs/1810.11804v1","url_pdf":"http://arxiv.org/pdf/1810.11804v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"gesture-generation","task_name":"Gesture Generation"},{"task_slug":"language-acquisition","task_name":"Language Acquisition"},{"task_slug":"negation","task_name":"Negation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/gesture-generation-on-beat","task":"Gesture Generation","dataset":"BEAT","model":"Seq2Seq","rank_in_archive_order":5,"of":5,"metrics":{"FID":"261.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}