{"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/sparkle-enhancing-sparql-generation-with","title":"SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding","arxiv_id":"2407.01626","date":"2024-06-29","proceeding":null,"authors":["Jaebok Lee","Hyeonjeong Shin"],"abstract":"Existing KBQA methods have traditionally relied on multi-stage methodologies, involving tasks such as entity linking, subgraph retrieval and query structure generation. However, multi-stage approaches are dependent on the accuracy of preceding steps, leading to cascading errors and increased inference time. Although a few studies have explored the use of end-to-end models, they often suffer from lower accuracy and generate inoperative query that is not supported by the underlying data. Furthermore, most prior approaches are limited to the static training data, potentially overlooking the evolving nature of knowledge bases over time. To address these challenges, we present a novel end-to-end natural language to SPARQL framework, SPARKLE. Notably SPARKLE leverages the structure of knowledge base directly during the decoding, effectively integrating knowledge into the query generation. Our study reveals that simply referencing knowledge base during inference significantly reduces the occurrence of inexecutable query generations. SPARKLE achieves new state-of-the-art results on SimpleQuestions-Wiki and highest F1 score on LCQuAD 1.0 (among models not using gold entities), while getting slightly lower result on the WebQSP dataset. Finally, we demonstrate SPARKLE's fast inference speed and its ability to adapt when the knowledge base differs between the training and inference stages.","url_abs":"https://arxiv.org/abs/2407.01626v1","url_pdf":"https://arxiv.org/pdf/2407.01626v1.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":"sparkle-enhancing-sparql-generation-with","repo_url":"https://github.com/zzaebok/sparkle","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"entity-linking","task_name":"Entity Linking"},{"task_slug":"knowledge-base-question-answering","task_name":"Knowledge Base Question Answering"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-base-question-answering-on-lc-quad","task":"Knowledge Base Question Answering","dataset":"LC-QuAD 1.0","model":"SPARKLE","rank_in_archive_order":3,"of":7,"metrics":{"F1":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-base-question-answering-on-4","task":"Knowledge Base Question Answering","dataset":"SimpleQuestionsWikiData","model":"SPARKLE","rank_in_archive_order":1,"of":5,"metrics":{"F1":"79.6"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-base-question-answering-on-1","task":"Knowledge Base Question Answering","dataset":"WebQuestionsSP","model":"SPARKLE","rank_in_archive_order":8,"of":8,"metrics":{"F1":"71.1","Hits@1":"71.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.01626","atlas_url":"https://app.syntology.ai/?focus=2407.01626","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":"2407.01626"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.01626\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.01626"},"call":"get_concepts_for_paper(arxiv_id=\"2407.01626\")"}],"by_repo":[{"repo":"zzaebok/sparkle","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":"79a449f5aa5e63b26f8d08e3832916f06fceb8990a6672c22a6820d6444dac79","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}