{"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/declarative-question-answering-over-knowledge","title":"Declarative Question Answering over Knowledge Bases containing Natural Language Text with Answer Set Programming","arxiv_id":"1905.00198","date":"2019-05-01","proceeding":null,"authors":["Arindam Mitra","Peter Clark","Oyvind Tafjord","Chitta Baral"],"abstract":"While in recent years machine learning (ML) based approaches have been the\npopular approach in developing end-to-end question answering systems, such\nsystems often struggle when additional knowledge is needed to correctly answer\nthe questions. Proposed alternatives involve translating the question and the\nnatural language text to a logical representation and then use logical\nreasoning. However, this alternative falters when the size of the text gets\nbigger. To address this we propose an approach that does logical reasoning over\npremises written in natural language text. The proposed method uses recent\nfeatures of Answer Set Programming (ASP) to call external NLP modules (which\nmay be based on ML) which perform simple textual entailment. To test our\napproach we develop a corpus based on the life cycle questions and showed that\nOur system achieves up to $18\\%$ performance gain when compared to standard MCQ\nsolvers.","url_abs":"http://arxiv.org/abs/1905.00198v1","url_pdf":"http://arxiv.org/pdf/1905.00198v1.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":"declarative-question-answering-over-knowledge","repo_url":"https://github.com/OpenSourceAI/sota-server","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1905.00198","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}