{"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/compositional-generalization-without-trees","title":"Compositional Generalization without Trees using Multiset Tagging and Latent Permutations","arxiv_id":"2305.16954","date":"2023-05-26","proceeding":null,"authors":["Matthias Lindemann","Alexander Koller","Ivan Titov"],"abstract":"Seq2seq models have been shown to struggle with compositional generalization in semantic parsing, i.e. generalizing to unseen compositions of phenomena that the model handles correctly in isolation. We phrase semantic parsing as a two-step process: we first tag each input token with a multiset of output tokens. Then we arrange the tokens into an output sequence using a new way of parameterizing and predicting permutations. We formulate predicting a permutation as solving a regularized linear program and we backpropagate through the solver. In contrast to prior work, our approach does not place a priori restrictions on possible permutations, making it very expressive. Our model outperforms pretrained seq2seq models and prior work on realistic semantic parsing tasks that require generalization to longer examples. We also outperform non-tree-based models on structural generalization on the COGS benchmark. For the first time, we show that a model without an inductive bias provided by trees achieves high accuracy on generalization to deeper recursion.","url_abs":"https://arxiv.org/abs/2305.16954v1","url_pdf":"https://arxiv.org/pdf/2305.16954v1.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":"compositional-generalization-without-trees","repo_url":"https://github.com/namednil/multiset-perm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"tag","task_name":"TAG"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.16954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16954"}},"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":"deterministic:regex_extraction","url":"https://github.com/namednil/multiset-perm","reach":null}],"summary":{"ran_fixture":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"18927973d0490737","entry":"bregman","repo":"namednil/multiset-perm","repo_kind":"official","path":"fertility/reordering/bregman_for_perm.py","file_url":"https://github.com/namednil/multiset-perm/blob/HEAD/fertility/reordering/bregman_for_perm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"18927973d0490737"}},{"code_sha256_prefix":"5972c5d0b7ae0ab5","entry":"in_place_omega_update","repo":"namednil/multiset-perm","repo_kind":"official","path":"fertility/reordering/bregman_for_perm.py","file_url":"https://github.com/namednil/multiset-perm/blob/HEAD/fertility/reordering/bregman_for_perm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5972c5d0b7ae0ab5"}},{"code_sha256_prefix":"cf177e1e5112b899","entry":"omega_update","repo":"namednil/multiset-perm","repo_kind":"official","path":"fertility/reordering/bregman_for_perm.py","file_url":"https://github.com/namednil/multiset-perm/blob/HEAD/fertility/reordering/bregman_for_perm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf177e1e5112b899"}},{"code_sha256_prefix":"d1d65ce4a829ba23","entry":"proj3","repo":"namednil/multiset-perm","repo_kind":"official","path":"fertility/reordering/bregman_for_perm.py","file_url":"https://github.com/namednil/multiset-perm/blob/HEAD/fertility/reordering/bregman_for_perm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1d65ce4a829ba23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}