{"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/capacity-bandwidth-and-compositionality-in","title":"Capacity, Bandwidth, and Compositionality in Emergent Language Learning","arxiv_id":"1910.11424","date":"2019-10-24","proceeding":null,"authors":["Cinjon Resnick","Abhinav Gupta","Jakob Foerster","Andrew M. Dai","Kyunghyun Cho"],"abstract":"Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compositionality. We note that most of those works have focused on communicative bandwidth as being of primary importance. While important, it is not the only contributing factor. In this paper, we investigate the learning biases that affect the efficacy and compositionality of emergent languages. Our foremost contribution is to explore how capacity of a neural network impacts its ability to learn a compositional language. We additionally introduce a set of evaluation metrics with which we analyze the learned languages. Our hypothesis is that there should be a specific range of model capacity and channel bandwidth that induces compositional structure in the resulting language and consequently encourages systematic generalization. While we empirically see evidence for the bottom of this range, we curiously do not find evidence for the top part of the range and believe that this is an open question for the community.","url_abs":"https://arxiv.org/abs/1910.11424v3","url_pdf":"https://arxiv.org/pdf/1910.11424v3.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":"capacity-bandwidth-and-compositionality-in","repo_url":"https://github.com/backpropper/cbc-emecom","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"systematic-generalization","task_name":"Systematic Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.11424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11424"}},"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/backpropper/cbc-emecom","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"044cf2a3ac20b2b7","entry":"cal_acc","repo":"backpropper/cbc-emecom","repo_kind":"official","path":"utils.py","file_url":"https://github.com/backpropper/cbc-emecom/blob/HEAD/utils.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":"044cf2a3ac20b2b7"}},{"code_sha256_prefix":"b58b3c933a79fc55","entry":"check_correct_preds","repo":"backpropper/cbc-emecom","repo_kind":"official","path":"utils.py","file_url":"https://github.com/backpropper/cbc-emecom/blob/HEAD/utils.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":"b58b3c933a79fc55"}},{"code_sha256_prefix":"a3ea15a80b8356c5","entry":"xent_loss","repo":"backpropper/cbc-emecom","repo_kind":"official","path":"utils.py","file_url":"https://github.com/backpropper/cbc-emecom/blob/HEAD/utils.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":"a3ea15a80b8356c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}