{"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/dynamic-integration-of-background-knowledge","title":"Dynamic Integration of Background Knowledge in Neural NLU Systems","arxiv_id":"1706.02596","date":"2017-06-08","proceeding":"ICLR 2018 1","authors":["Dirk Weissenborn","Tomáš Kočiský","Chris Dyer"],"abstract":"Common-sense and background knowledge is required to understand natural\nlanguage, but in most neural natural language understanding (NLU) systems, this\nknowledge must be acquired from training corpora during learning, and then it\nis static at test time. We introduce a new architecture for the dynamic\nintegration of explicit background knowledge in NLU models. A general-purpose\nreading module reads background knowledge in the form of free-text statements\n(together with task-specific text inputs) and yields refined word\nrepresentations to a task-specific NLU architecture that reprocesses the task\ninputs with these representations. Experiments on document question answering\n(DQA) and recognizing textual entailment (RTE) demonstrate the effectiveness\nand flexibility of the approach. Analysis shows that our model learns to\nexploit knowledge in a semantically appropriate way.","url_abs":"http://arxiv.org/abs/1706.02596v3","url_pdf":"http://arxiv.org/pdf/1706.02596v3.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":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"rte","task_name":"RTE"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"Reading Twice for NLU","rank_in_archive_order":44,"of":56,"metrics":{"EM":"50.56","F1":"56.73"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.02596","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}