{"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/modeling-natural-language-emergence-with","title":"Modeling natural language emergence with integral transform theory and reinforcement learning","arxiv_id":"1812.01431","date":"2018-11-30","proceeding":null,"authors":["Bohdan Khomtchouk","Shyam Sudhakaran"],"abstract":"Zipf's law predicts a power-law relationship between word rank and frequency\nin language communication systems and has been widely reported in a variety of\nnatural language processing applications. However, the emergence of natural\nlanguage is often modeled as a function of bias between speaker and listener\ninterests, which lacks a direct way of relating information-theoretic bias to\nZipfian rank. A function of bias also serves as an unintuitive interpretation\nof the communicative effort exchanged between a speaker and a listener. We\ncounter these shortcomings by proposing a novel integral transform and kernel\nfor mapping communicative bias functions to corresponding word frequency-rank\nrepresentations at any arbitrary phase transition point, resulting in a direct\nway to link communicative effort (modeled by speaker/listener bias) to specific\nvocabulary used (represented by word rank). We demonstrate the practical\nutility of our integral transform by showing how a change from bias to rank\nresults in greater accuracy and performance at an image classification task for\nassigning word labels to images randomly subsampled from CIFAR10. We model this\ntask as a reinforcement learning game between a speaker and listener and\ncompare the relative impact of bias and Zipfian word rank on communicative\nperformance (and accuracy) between the two agents.","url_abs":"http://arxiv.org/abs/1812.01431v1","url_pdf":"http://arxiv.org/pdf/1812.01431v1.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":"modeling-natural-language-emergence-with","repo_url":"https://github.com/Quiltomics/NLERL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}