{"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/weakly-supervised-semantic-parsing-with-1","title":"Weakly-supervised Semantic Parsing with Abstract Examples","arxiv_id":"1711.05240","date":"2017-11-14","proceeding":null,"authors":["Omer Goldman","Veronica Latcinnik","Udi Naveh","Amir Globerson","Jonathan Berant"],"abstract":"Training semantic parsers from weak supervision (denotations) rather than\nstrong supervision (programs) complicates training in two ways. First, a large\nsearch space of potential programs needs to be explored at training time to\nfind a correct program. Second, spurious programs that accidentally lead to a\ncorrect denotation add noise to training. In this work we propose that in\nclosed worlds with clear semantic types, one can substantially alleviate these\nproblems by utilizing an abstract representation, where tokens in both the\nlanguage utterance and program are lifted to an abstract form. We show that\nthese abstractions can be defined with a handful of lexical rules and that they\nresult in sharing between different examples that alleviates the difficulties\nin training. To test our approach, we develop the first semantic parser for\nCNLVR, a challenging visual reasoning dataset, where the search space is large\nand overcoming spuriousness is critical, because denotations are either TRUE or\nFALSE, and thus random programs are likely to lead to a correct denotation. Our\nmethod substantially improves performance, and reaches 82.5% accuracy, a 14.7%\nabsolute accuracy improvement compared to the best reported accuracy so far.","url_abs":"http://arxiv.org/abs/1711.05240v5","url_pdf":"http://arxiv.org/pdf/1711.05240v5.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":"weakly-supervised-semantic-parsing-with-1","repo_url":"https://github.com/udiNaveh/nlvr_tau_nlp_final_proj","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.05240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05240"}},"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/udiNaveh/nlvr_tau_nlp_final_proj","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"65025751f45d79c2","entry":"read_data","repo":"udiNaveh/nlvr_tau_nlp_final_proj","repo_kind":"official","path":"data_manager.py","file_url":"https://github.com/udiNaveh/nlvr_tau_nlp_final_proj/blob/HEAD/data_manager.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":"65025751f45d79c2"}},{"code_sha256_prefix":"f98f66c99de6e7d6","entry":"get_next_token_probs_from_nn","repo":"udiNaveh/nlvr_tau_nlp_final_proj","repo_kind":"official","path":"seq2seqModel/seq2seq.py","file_url":"https://github.com/udiNaveh/nlvr_tau_nlp_final_proj/blob/HEAD/seq2seqModel/seq2seq.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":"f98f66c99de6e7d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}