{"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/interactive-language-acquisition-with-one","title":"Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game","arxiv_id":"1805.00462","date":"2018-04-26","proceeding":"ACL 2018 7","authors":["Haichao Zhang","Haonan Yu","Wei Xu"],"abstract":"Building intelligent agents that can communicate with and learn from humans\nin natural language is of great value. Supervised language learning is limited\nby the ability of capturing mainly the statistics of training data, and is\nhardly adaptive to new scenarios or flexible for acquiring new knowledge\nwithout inefficient retraining or catastrophic forgetting. We highlight the\nperspective that conversational interaction serves as a natural interface both\nfor language learning and for novel knowledge acquisition and propose a joint\nimitation and reinforcement approach for grounded language learning through an\ninteractive conversational game. The agent trained with this approach is able\nto actively acquire information by asking questions about novel objects and use\nthe just-learned knowledge in subsequent conversations in a one-shot fashion.\nResults compared with other methods verified the effectiveness of the proposed\napproach.","url_abs":"http://arxiv.org/abs/1805.00462v1","url_pdf":"http://arxiv.org/pdf/1805.00462v1.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":[{"paper_slug":"interactive-language-acquisition-with-one","repo_url":"https://github.com/PaddlePaddle/XWorld","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"grounded-language-learning","task_name":"Grounded language learning"},{"task_slug":"language-acquisition","task_name":"Language Acquisition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.00462","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}