{"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/learning-with-latent-language","title":"Learning with Latent Language","arxiv_id":"1711.00482","date":"2017-11-01","proceeding":"NAACL 2018 6","authors":["Jacob Andreas","Dan Klein","Sergey Levine"],"abstract":"The named concepts and compositional operators present in natural language\nprovide a rich source of information about the kinds of abstractions humans use\nto navigate the world. Can this linguistic background knowledge improve the\ngenerality and efficiency of learned classifiers and control policies? This\npaper aims to show that using the space of natural language strings as a\nparameter space is an effective way to capture natural task structure. In a\npretraining phase, we learn a language interpretation model that transforms\ninputs (e.g. images) into outputs (e.g. labels) given natural language\ndescriptions. To learn a new concept (e.g. a classifier), we search directly in\nthe space of descriptions to minimize the interpreter's loss on training\nexamples. Crucially, our models do not require language data to learn these\nconcepts: language is used only in pretraining to impose structure on\nsubsequent learning. Results on image classification, text editing, and\nreinforcement learning show that, in all settings, models with a linguistic\nparameterization outperform those without.","url_abs":"http://arxiv.org/abs/1711.00482v1","url_pdf":"http://arxiv.org/pdf/1711.00482v1.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":"learning-with-latent-language","repo_url":"https://github.com/jacobandreas/l3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.00482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00482"}},"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/jacobandreas/l3","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"56b9de9f5cc2133a","entry":"flatten","repo":"jacobandreas/l3","repo_kind":"official","path":"misc/util.py","file_url":"https://github.com/jacobandreas/l3/blob/HEAD/misc/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56b9de9f5cc2133a"}},{"code_sha256_prefix":"04d4777b58b16f4b","entry":"pad_slice","repo":"jacobandreas/l3","repo_kind":"official","path":"misc/array.py","file_url":"https://github.com/jacobandreas/l3/blob/HEAD/misc/array.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04d4777b58b16f4b"}},{"code_sha256_prefix":"bd4ddcaa3bde00a9","entry":"parse_fexp","repo":"jacobandreas/l3","repo_kind":"official","path":"misc/util.py","file_url":"https://github.com/jacobandreas/l3/blob/HEAD/misc/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd4ddcaa3bde00a9"}},{"code_sha256_prefix":"bef84cd330780883","entry":"tree_map","repo":"jacobandreas/l3","repo_kind":"official","path":"misc/util.py","file_url":"https://github.com/jacobandreas/l3/blob/HEAD/misc/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bef84cd330780883"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}