{"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/a-two-stage-approach-towards-generalization-1","title":"A Two-Stage Approach towards Generalization in Knowledge Base Question Answering","arxiv_id":null,"date":"2022-01-16","proceeding":"ACL ARR January 2022 1","authors":["Anonymous"],"abstract":"Most existing approaches for Knowledge Base Question Answering (KBQA) focus on a specific underlying knowledge base either because of inherent assumptions in the approach, or because evaluating it on a different knowledge base requires non-trivial changes. However, many popular knowledge bases share similarities in their underlying schemas that can be leveraged to facilitate generalization across knowledge bases. To achieve this generalization, we introduce a KBQA framework based on a  2-stage architecture that explicitly separates semantic parsing from the knowledge base interaction, facilitating transfer learning across datasets and knowledge graphs. We show that pretraining on datasets with a different underlying knowledge base can nevertheless provide significant performance gains and reduce sample complexity. Our approach achieves comparable or state-of-the-art performance for LC-QuAD (DBpedia), WebQSP (Freebase), SimpleQuestions (Wikidata) and MetaQA (Wikimovies-KG). ","url_abs":"https://openreview.net/forum?id=-5R9TsypRrW","url_pdf":"https://openreview.net/pdf?id=-5R9TsypRrW","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":[],"tasks":[{"task_slug":"knowledge-base-question-answering","task_name":"Knowledge Base Question Answering"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"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":"STaG-QA","rank_in_archive_order":5,"of":7,"metrics":{"F1":"53.6"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-base-question-answering-on-4","task":"Knowledge Base Question Answering","dataset":"SimpleQuestionsWikiData","model":"STaG-QA","rank_in_archive_order":3,"of":5,"metrics":{"F1":"61.2"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}