{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/counterfactual-learning-from-human","title":"Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing","arxiv_id":"1811.12239","date":"2018-11-29","proceeding":null,"authors":["Carolin Lawrence","Stefan Riezler"],"abstract":"In semantic parsing for question-answering, it is often too expensive to\ncollect gold parses or even gold answers as supervision signals. We propose to\nconvert model outputs into a set of human-understandable statements which allow\nnon-expert users to act as proofreaders, providing error markings as learning\nsignals to the parser. Because model outputs were suggested by a historic\nsystem, we operate in a counterfactual, or off-policy, learning setup. We\nintroduce new estimators which can effectively leverage the given feedback and\nwhich avoid known degeneracies in counterfactual learning, while still being\napplicable to stochastic gradient optimization for neural semantic parsing.\nFurthermore, we discuss how our feedback collection method can be seamlessly\nintegrated into deployed virtual personal assistants that embed a semantic\nparser. Our work is the first to show that semantic parsers can be improved\nsignificantly by counterfactual learning from logged human feedback data.","url_abs":"http://arxiv.org/abs/1811.12239v1","url_pdf":"http://arxiv.org/pdf/1811.12239v1.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":"counterfactual-learning-from-human","repo_url":"https://github.com/carolinlawrence/nematus","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"carolinlawrence/nematus","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1805.01252"],"harvested_for_calls":[{"arxiv_id":"1805.01252","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1805.01252"},"call":"get_harvested_code_for_paper(arxiv_id=\"1805.01252\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"84bf3ccec3532b9022b524a872d885729f5cceb673e5250380bec543cf4bc664","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}