{"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/generating-formulaic-text-by-splicing","title":"Data-to-text Generation by Splicing Together Nearest Neighbors","arxiv_id":"2101.08248","date":"2021-01-20","proceeding":"EMNLP 2021 11","authors":["Sam Wiseman","Arturs Backurs","Karl Stratos"],"abstract":"We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from \"neighbor\" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token, left-to-right, we learn a policy that directly manipulates segments of neighbor text, by inserting or replacing them in partially constructed generations. Standard techniques for training such a policy require an oracle derivation for each generation, and we prove that finding the shortest such derivation can be reduced to parsing under a particular weighted context-free grammar. We find that policies learned in this way perform on par with strong baselines in terms of automatic and human evaluation, but allow for more interpretable and controllable generation.","url_abs":"https://arxiv.org/abs/2101.08248v4","url_pdf":"https://arxiv.org/pdf/2101.08248v4.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":"generating-formulaic-text-by-splicing","repo_url":"https://github.com/swiseman/neighbor-splicing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conditional-text-generation","task_name":"Conditional Text Generation"},{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2101.08248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08248"}},"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/swiseman/neighbor-splicing","reach":null}],"summary":{"ran":1,"ran_honours":2,"ran_fixture":4,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":10,"samples":[{"code_sha256_prefix":"dcb4455b9661f0c9","entry":"Hyp","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcb4455b9661f0c9"}},{"code_sha256_prefix":"3d43725ce088f540","entry":"endidx2pred","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d43725ce088f540"}},{"code_sha256_prefix":"4be5b29079791381","entry":"get_endstuff","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4be5b29079791381"}},{"code_sha256_prefix":"b5b9e6d3a4d88223","entry":"get_leftright_endstuff","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5b9e6d3a4d88223"}},{"code_sha256_prefix":"a8da01659e2b62f9","entry":"get_trace","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.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":"a8da01659e2b62f9"}},{"code_sha256_prefix":"a77612b337ec94d7","entry":"get_updated_canvs","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a77612b337ec94d7"}},{"code_sha256_prefix":"7589dead6d061a1f","entry":"init_search","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7589dead6d061a1f"}},{"code_sha256_prefix":"7281b50bbf89daa6","entry":"make_nemask","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.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":"7281b50bbf89daa6"}},{"code_sha256_prefix":"b42f39e814ed2611","entry":"startidx2pred","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b42f39e814ed2611"}},{"code_sha256_prefix":"8bc22af12da5dab7","entry":"se_search","repo":"swiseman/neighbor-splicing","repo_kind":"official","path":"se_search.py","file_url":"https://github.com/swiseman/neighbor-splicing/blob/HEAD/se_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8bc22af12da5dab7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}