{"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/hierarchical-sketch-induction-for-paraphrase","title":"Hierarchical Sketch Induction for Paraphrase Generation","arxiv_id":"2203.03463","date":"2022-03-07","proceeding":"ACL 2022 5","authors":["Tom Hosking","Hao Tang","Mirella Lapata"],"abstract":"We propose a generative model of paraphrase generation, that encourages syntactic diversity by conditioning on an explicit syntactic sketch. We introduce Hierarchical Refinement Quantized Variational Autoencoders (HRQ-VAE), a method for learning decompositions of dense encodings as a sequence of discrete latent variables that make iterative refinements of increasing granularity. This hierarchy of codes is learned through end-to-end training, and represents fine-to-coarse grained information about the input. We use HRQ-VAE to encode the syntactic form of an input sentence as a path through the hierarchy, allowing us to more easily predict syntactic sketches at test time. Extensive experiments, including a human evaluation, confirm that HRQ-VAE learns a hierarchical representation of the input space, and generates paraphrases of higher quality than previous systems.","url_abs":"https://arxiv.org/abs/2203.03463v2","url_pdf":"https://arxiv.org/pdf/2203.03463v2.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":"hierarchical-sketch-induction-for-paraphrase","repo_url":"https://github.com/tomhosking/hrq-vae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"paraphrase-generation","task_name":"Paraphrase Generation"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/paraphrase-generation-on-mscoco","task":"Paraphrase Generation","dataset":"MSCOCO","model":"HRQ-VAE","rank_in_archive_order":1,"of":1,"metrics":{"BLEU":"27.90","iBLEU":"19.04"},"uses_additional_data":false},{"leaderboard":"/sota/paraphrase-generation-on-paralex","task":"Paraphrase Generation","dataset":"Paralex","model":"HRQ-VAE","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"39.49","iBLEU":"24.93"},"uses_additional_data":false},{"leaderboard":"/sota/paraphrase-generation-on-quora-question-pairs-1","task":"Paraphrase Generation","dataset":"Quora Question Pairs","model":"HRQ-VAE","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"33.11","iBLEU":"18.42"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.03463","atlas_url":"https://app.syntology.ai/?focus=2203.03463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03463"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/tomhosking/hrq-vae","reach":null}],"summary":{"ran":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"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":"c364aa6f0d042d54","entry":"HierarchicalRefinementQuantizer","repo":"tomhosking/hrq-vae","repo_kind":"official","path":"src/hrq_vae.py","file_url":"https://github.com/tomhosking/hrq-vae/blob/HEAD/src/hrq_vae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c364aa6f0d042d54"}},{"code_sha256_prefix":"af51b6b925efb7fe","entry":"cos_sim","repo":"tomhosking/hrq-vae","repo_kind":"official","path":"src/hrq_vae.py","file_url":"https://github.com/tomhosking/hrq-vae/blob/HEAD/src/hrq_vae.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af51b6b925efb7fe"}},{"code_sha256_prefix":"1e275a2e8b64d8a0","entry":"onehot","repo":"tomhosking/hrq-vae","repo_kind":"official","path":"src/hrq_vae.py","file_url":"https://github.com/tomhosking/hrq-vae/blob/HEAD/src/hrq_vae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e275a2e8b64d8a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}