{"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/measuring-compositionality-in-representation","title":"Measuring Compositionality in Representation Learning","arxiv_id":"1902.07181","date":"2019-02-19","proceeding":"ICLR 2019 5","authors":["Jacob Andreas"],"abstract":"Many machine learning algorithms represent input data with vector embeddings\nor discrete codes. When inputs exhibit compositional structure (e.g. objects\nbuilt from parts or procedures from subroutines), it is natural to ask whether\nthis compositional structure is reflected in the the inputs' learned\nrepresentations. While the assessment of compositionality in languages has\nreceived significant attention in linguistics and adjacent fields, the machine\nlearning literature lacks general-purpose tools for producing graded\nmeasurements of compositional structure in more general (e.g. vector-valued)\nrepresentation spaces. We describe a procedure for evaluating compositionality\nby measuring how well the true representation-producing model can be\napproximated by a model that explicitly composes a collection of inferred\nrepresentational primitives. We use the procedure to provide formal and\nempirical characterizations of compositional structure in a variety of\nsettings, exploring the relationship between compositionality and learning\ndynamics, human judgments, representational similarity, and generalization.","url_abs":"http://arxiv.org/abs/1902.07181v2","url_pdf":"http://arxiv.org/pdf/1902.07181v2.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":"measuring-compositionality-in-representation","repo_url":"https://github.com/jacobandreas/tre","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.07181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.07181"}},"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/tre","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"585f0ee738e01750","entry":"flatten","repo":"jacobandreas/tre","repo_kind":"official","path":"util.py","file_url":"https://github.com/jacobandreas/tre/blob/HEAD/util.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"585f0ee738e01750"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}