{"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-transductions-to-test-systematic","title":"Benchmarking Compositionality with Formal Languages","arxiv_id":"2208.08195","date":"2022-08-17","proceeding":"COLING 2022 10","authors":["Josef Valvoda","Naomi Saphra","Jonathan Rawski","Adina Williams","Ryan Cotterell"],"abstract":"Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability. Whether large neural models in NLP can acquire this ability while learning from data is an open question. In this paper, we investigate this problem from the perspective of formal languages. We use deterministic finite-state transducers to make an unbounded number of datasets with controllable properties governing compositionality. By randomly sampling over many transducers, we explore which of their properties contribute to learnability of a compositional relation by a neural network. We find that the models either learn the relations completely or not at all. The key is transition coverage, setting a soft learnability limit at 400 examples per transition.","url_abs":"https://arxiv.org/abs/2208.08195v3","url_pdf":"https://arxiv.org/pdf/2208.08195v3.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-transductions-to-test-systematic","repo_url":"https://github.com/valvoda/neuraltransducer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.08195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.08195"}},"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/valvoda/neuraltransducer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":"a3e27bd1e8b628ed","entry":"Embedding","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/src/transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3e27bd1e8b628ed"}},{"code_sha256_prefix":"8cd8cb0d1e9e63e4","entry":"Linear","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/src/transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd8cb0d1e9e63e4"}},{"code_sha256_prefix":"e75d3bbaec7257ef","entry":"fancy_gather","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/src/model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e75d3bbaec7257ef"}},{"code_sha256_prefix":"6770850b6271c818","entry":"dummy_mask","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/src/model.py","link_basis":"harvester_set","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":"6770850b6271c818"}},{"code_sha256_prefix":"c12921cb3468831c","entry":"find_split","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"dataset_generator.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/dataset_generator.py","link_basis":"harvester_set","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":"c12921cb3468831c"}},{"code_sha256_prefix":"03bea59a9689bb8f","entry":"get_logger","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/src/util.py","link_basis":"harvester_set","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":"03bea59a9689bb8f"}},{"code_sha256_prefix":"693fef0d16061a2b","entry":"get_temp_log_filename","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/src/util.py","link_basis":"harvester_set","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":"693fef0d16061a2b"}},{"code_sha256_prefix":"eb97ec33109d48b7","entry":"grad_norm","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/src/util.py","link_basis":"harvester_set","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":"eb97ec33109d48b7"}},{"code_sha256_prefix":"9a67703c4f6f0e07","entry":"model_func","repo":"valvoda/neuraltransducer","repo_kind":"official","path":"get_results.py","file_url":"https://github.com/valvoda/neuraltransducer/blob/HEAD/get_results.py","link_basis":"harvester_set","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":"9a67703c4f6f0e07"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}