{"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/towards-dynamic-computation-graphs-via-sparse","title":"Towards Dynamic Computation Graphs via Sparse Latent Structure","arxiv_id":"1809.00653","date":"2018-09-03","proceeding":"EMNLP 2018 10","authors":["Vlad Niculae","André F. T. Martins","Claire Cardie"],"abstract":"Deep NLP models benefit from underlying structures in the data---e.g., parse\ntrees---typically extracted using off-the-shelf parsers. Recent attempts to\njointly learn the latent structure encounter a tradeoff: either make\nfactorization assumptions that limit expressiveness, or sacrifice end-to-end\ndifferentiability. Using the recently proposed SparseMAP inference, which\nretrieves a sparse distribution over latent structures, we propose a novel\napproach for end-to-end learning of latent structure predictors jointly with a\ndownstream predictor. To the best of our knowledge, our method is the first to\nenable unrestricted dynamic computation graph construction from the global\nlatent structure, while maintaining differentiability.","url_abs":"http://arxiv.org/abs/1809.00653v1","url_pdf":"http://arxiv.org/pdf/1809.00653v1.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":"towards-dynamic-computation-graphs-via-sparse","repo_url":"https://github.com/vene/sparsemap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00653"}},"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/vene/sparsemap","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"3c0ed1909a49c1cd","entry":"S_from_Ainv","repo":"vene/sparsemap","repo_kind":"official","path":"python/sparsemap/utils.py","file_url":"https://github.com/vene/sparsemap/blob/HEAD/python/sparsemap/utils.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":"3c0ed1909a49c1cd"}},{"code_sha256_prefix":"899dea72accf57c0","entry":"batch_slices","repo":"vene/sparsemap","repo_kind":"official","path":"python/sparsemap/utils.py","file_url":"https://github.com/vene/sparsemap/blob/HEAD/python/sparsemap/utils.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":"899dea72accf57c0"}},{"code_sha256_prefix":"62ad6be27a4c6644","entry":"expand_with_zeros","repo":"vene/sparsemap","repo_kind":"official","path":"python/sparsemap/utils.py","file_url":"https://github.com/vene/sparsemap/blob/HEAD/python/sparsemap/utils.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":"62ad6be27a4c6644"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}