{"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/universal-linguistic-inductive-biases-via","title":"Universal linguistic inductive biases via meta-learning","arxiv_id":"2006.16324","date":"2020-06-29","proceeding":null,"authors":["R. Thomas McCoy","Erin Grant","Paul Smolensky","Thomas L. Griffiths","Tal Linzen"],"abstract":"How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it is unclear which inductive biases can explain observed patterns in language acquisition. To facilitate computational modeling aimed at addressing this question, we introduce a framework for giving particular linguistic inductive biases to a neural network model; such a model can then be used to empirically explore the effects of those inductive biases. This framework disentangles universal inductive biases, which are encoded in the initial values of a neural network's parameters, from non-universal factors, which the neural network must learn from data in a given language. The initial state that encodes the inductive biases is found with meta-learning, a technique through which a model discovers how to acquire new languages more easily via exposure to many possible languages. By controlling the properties of the languages that are used during meta-learning, we can control the inductive biases that meta-learning imparts. We demonstrate this framework with a case study based on syllable structure. First, we specify the inductive biases that we intend to give our model, and then we translate those inductive biases into a space of languages from which a model can meta-learn. Finally, using existing analysis techniques, we verify that our approach has imparted the linguistic inductive biases that it was intended to impart.","url_abs":"https://arxiv.org/abs/2006.16324v1","url_pdf":"https://arxiv.org/pdf/2006.16324v1.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":"universal-linguistic-inductive-biases-via","repo_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-acquisition","task_name":"Language Acquisition"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.16324","atlas_url":"https://app.syntology.ai/?focus=2006.16324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16324"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/tommccoy1/meta-learning-linguistic-biases","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":12},"by_repo_kind":{"official":{"samples":12,"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":"85e4d241e1cf8c37","entry":"create_input_output_list","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/mix_input_outputs.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/mix_input_outputs.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":"85e4d241e1cf8c37"}},{"code_sha256_prefix":"1dae4dca4528bfe9","entry":"filtering_function","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/make_tasks.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/make_tasks.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":"1dae4dca4528bfe9"}},{"code_sha256_prefix":"c96a270fe2e4246e","entry":"filtering_function","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/make_tasks_imp.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/make_tasks_imp.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":"c96a270fe2e4246e"}},{"code_sha256_prefix":"8fc96794bf65fee5","entry":"fit_task","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/training.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/training.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":"8fc96794bf65fee5"}},{"code_sha256_prefix":"5d39fdcf930386ac","entry":"generate_cv","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/phonology_task_creation.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/phonology_task_creation.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":"5d39fdcf930386ac"}},{"code_sha256_prefix":"4f17c23a7bcad057","entry":"generate_cv_cumul","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/phonology_task_creation.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/phonology_task_creation.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":"4f17c23a7bcad057"}},{"code_sha256_prefix":"cbb995366ddbecb7","entry":"get_loss","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/training.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/training.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":"cbb995366ddbecb7"}},{"code_sha256_prefix":"71c23e4f8efd7c75","entry":"load_dataset","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/load_data.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/load_data.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":"71c23e4f8efd7c75"}},{"code_sha256_prefix":"e9e17a0d425b889c","entry":"load_io","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/load_data.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/load_data.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":"e9e17a0d425b889c"}},{"code_sha256_prefix":"4daaff7ba7e8a2fb","entry":"load_languages","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/load_data.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/load_data.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":"4daaff7ba7e8a2fb"}},{"code_sha256_prefix":"7a6c415682d544bd","entry":"phoneme_inventory","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/phonology_task_creation.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/phonology_task_creation.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":"7a6c415682d544bd"}},{"code_sha256_prefix":"b054155a2bd18a30","entry":"train_model","repo":"tommccoy1/meta-learning-linguistic-biases","repo_kind":"official","path":"src/training.py","file_url":"https://github.com/tommccoy1/meta-learning-linguistic-biases/blob/HEAD/src/training.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":"b054155a2bd18a30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}