{"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/compositional-language-understanding-with","title":"Compositional Language Understanding with Text-based Relational Reasoning","arxiv_id":"1811.02959","date":"2018-11-07","proceeding":null,"authors":["Koustuv Sinha","Shagun Sodhani","William L. Hamilton","Joelle Pineau"],"abstract":"Neural networks for natural language reasoning have largely focused on\nextractive, fact-based question-answering (QA) and common-sense inference.\nHowever, it is also crucial to understand the extent to which neural networks\ncan perform relational reasoning and combinatorial generalization from natural\nlanguage---abilities that are often obscured by annotation artifacts and the\ndominance of language modeling in standard QA benchmarks. In this work, we\npresent a novel benchmark dataset for language understanding that isolates\nperformance on relational reasoning. We also present a neural message-passing\nbaseline and show that this model, which incorporates a relational inductive\nbias, is superior at combinatorial generalization compared to a traditional\nrecurrent neural network approach.","url_abs":"http://arxiv.org/abs/1811.02959v2","url_pdf":"http://arxiv.org/pdf/1811.02959v2.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":"compositional-language-understanding-with","repo_url":"https://github.com/koustuvsinha/clutrr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"compositional-language-understanding-with","repo_url":"https://github.com/koustuvsinha/clutrr-workshop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.02959","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}