{"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/compositional-languages-emerge-in-a-neural-1","title":"Compositional Languages Emerge in a Neural Iterated Learning Model","arxiv_id":"2002.01365","date":"2020-02-04","proceeding":"ICLR 2020 1","authors":["Yi Ren","Shangmin Guo","Matthieu Labeau","Shay B. Cohen","Simon Kirby"],"abstract":"The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary. If compositionality is indeed a natural property of language, we may expect it to appear in communication protocols that are created by neural agents in language games. In this paper, we propose an effective neural iterated learning (NIL) algorithm that, when applied to interacting neural agents, facilitates the emergence of a more structured type of language. Indeed, these languages provide learning speed advantages to neural agents during training, which can be incrementally amplified via NIL. We provide a probabilistic model of NIL and an explanation of why the advantage of compositional language exist. Our experiments confirm our analysis, and also demonstrate that the emerged languages largely improve the generalizing power of the neural agent communication.","url_abs":"https://arxiv.org/abs/2002.01365v2","url_pdf":"https://arxiv.org/pdf/2002.01365v2.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":"compositional-languages-emerge-in-a-neural-1","repo_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.01365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.01365"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"54d2d2202334e3b0","entry":"cat_softmax","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/models/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54d2d2202334e3b0"}},{"code_sha256_prefix":"618f6c2d8b6a4b33","entry":"edit_dist","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/result_record.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/result_record.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"618f6c2d8b6a4b33"}},{"code_sha256_prefix":"06863a600040ac40","entry":"get_lis_curve_msg","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/manual_language_gen.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/manual_language_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06863a600040ac40"}},{"code_sha256_prefix":"330aa6cf303d25f9","entry":"hanmming_dist","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/result_record.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/result_record.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"330aa6cf303d25f9"}},{"code_sha256_prefix":"507445982b6df2d6","entry":"key_to_value","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/manual_language_gen.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/manual_language_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"507445982b6df2d6"}},{"code_sha256_prefix":"82dba4ec6b8597c4","entry":"num_compositional","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/__language_types.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/__language_types.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82dba4ec6b8597c4"}},{"code_sha256_prefix":"bde7360c494fa179","entry":"num_holi_comp","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/__language_types.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/__language_types.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bde7360c494fa179"}},{"code_sha256_prefix":"5c008778ef447369","entry":"valid_list_gen","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/data_gen.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/data_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c008778ef447369"}},{"code_sha256_prefix":"bd2406d53ad12686","entry":"value_to_onehot","repo":"Joshua-Ren/Neural_Iterated_Learning","repo_kind":"official","path":"utils/manual_language_gen.py","file_url":"https://github.com/Joshua-Ren/Neural_Iterated_Learning/blob/HEAD/utils/manual_language_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd2406d53ad12686"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}