{"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/neural-multi-step-reasoning-for-question","title":"Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables","arxiv_id":"1702.06589","date":"2017-02-21","proceeding":null,"authors":["Till Haug","Octavian-Eugen Ganea","Paulina Grnarova"],"abstract":"Advances in natural language processing tasks have gained momentum in recent\nyears due to the increasingly popular neural network methods. In this paper, we\nexplore deep learning techniques for answering multi-step reasoning questions\nthat operate on semi-structured tables. Challenges here arise from the level of\nlogical compositionality expressed by questions, as well as the domain\nopenness. Our approach is weakly supervised, trained on question-answer-table\ntriples without requiring intermediate strong supervision. It performs two\nphases: first, machine understandable logical forms (programs) are generated\nfrom natural language questions following the work of [Pasupat and Liang,\n2015]. Second, paraphrases of logical forms and questions are embedded in a\njointly learned vector space using word and character convolutional neural\nnetworks. A neural scoring function is further used to rank and retrieve the\nmost probable logical form (interpretation) of a question. Our best single\nmodel achieves 34.8% accuracy on the WikiTableQuestions dataset, while the best\nensemble of our models pushes the state-of-the-art score on this task to 38.7%,\nthus slightly surpassing both the engineered feature scoring baseline, as well\nas the Neural Programmer model of [Neelakantan et al., 2016].","url_abs":"http://arxiv.org/abs/1702.06589v2","url_pdf":"http://arxiv.org/pdf/1702.06589v2.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":"neural-multi-step-reasoning-for-question","repo_url":"https://github.com/dalab/neural_qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.06589","atlas_url":"https://app.syntology.ai/?focus=1702.06589","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1702.06589"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1702.06589\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1702.06589"},"call":"get_concepts_for_paper(arxiv_id=\"1702.06589\")"}],"by_repo":[{"repo":"dalab/neural_qa","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"ad006a8f0eef2e81305e33b4b37c9e9a040ce47cbf00604d951c0d051e68be76","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}