{"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/case-based-reasoning-for-natural-language","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","arxiv_id":"2104.08762","date":"2021-04-18","proceeding":"EMNLP 2021 11","authors":["Rajarshi Das","Manzil Zaheer","Dung Thai","Ameya Godbole","Ethan Perez","Jay-Yoon Lee","Lizhen Tan","Lazaros Polymenakos","Andrew McCallum"],"abstract":"It is often challenging to solve a complex problem from scratch, but much easier if we can access other similar problems with their solutions -- a paradigm known as case-based reasoning (CBR). We propose a neuro-symbolic CBR approach (CBR-KBQA) for question answering over large knowledge bases. CBR-KBQA consists of a nonparametric memory that stores cases (question and logical forms) and a parametric model that can generate a logical form for a new question by retrieving cases that are relevant to it. On several KBQA datasets that contain complex questions, CBR-KBQA achieves competitive performance. For example, on the ComplexWebQuestions dataset, CBR-KBQA outperforms the current state of the art by 11\\% on accuracy. Furthermore, we show that CBR-KBQA is capable of using new cases \\emph{without} any further training: by incorporating a few human-labeled examples in the case memory, CBR-KBQA is able to successfully generate logical forms containing unseen KB entities as well as relations.","url_abs":"https://arxiv.org/abs/2104.08762v2","url_pdf":"https://arxiv.org/pdf/2104.08762v2.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":[],"tasks":[{"task_slug":"knowledge-base-question-answering","task_name":"Knowledge Base Question Answering"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-base-question-answering-on","task":"Knowledge Base Question Answering","dataset":"ComplexWebQuestions","model":"CBR-KBQA","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"70.4"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-base-question-answering-on","task":"Knowledge Base Question Answering","dataset":"ComplexWebQuestions","model":"PullNet","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-base-question-answering-on","task":"Knowledge Base Question Answering","dataset":"ComplexWebQuestions","model":"QGG","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"44.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-parsing-on-webquestionssp","task":"Semantic Parsing","dataset":"WebQuestionsSP","model":"CBR-KBQA","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"70"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.08762","atlas_url":"https://app.syntology.ai/?focus=2104.08762","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}