{"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/an-interpretable-reasoning-network-for-multi","title":"An Interpretable Reasoning Network for Multi-Relation Question Answering","arxiv_id":"1801.04726","date":"2018-01-15","proceeding":"COLING 2018 8","authors":["Mantong Zhou","Minlie Huang","Xiaoyan Zhu"],"abstract":"Multi-relation Question Answering is a challenging task, due to the\nrequirement of elaborated analysis on questions and reasoning over multiple\nfact triples in knowledge base. In this paper, we present a novel model called\nInterpretable Reasoning Network that employs an interpretable, hop-by-hop\nreasoning process for question answering. The model dynamically decides which\npart of an input question should be analyzed at each hop; predicts a relation\nthat corresponds to the current parsed results; utilizes the predicted relation\nto update the question representation and the state of the reasoning process;\nand then drives the next-hop reasoning. Experiments show that our model yields\nstate-of-the-art results on two datasets. More interestingly, the model can\noffer traceable and observable intermediate predictions for reasoning analysis\nand failure diagnosis, thereby allowing manual manipulation in predicting the\nfinal answer.","url_abs":"http://arxiv.org/abs/1801.04726v3","url_pdf":"http://arxiv.org/pdf/1801.04726v3.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":"an-interpretable-reasoning-network-for-multi","repo_url":"https://github.com/zmtkeke/IRN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[{"slug":"pathquestion","name":"PathQuestion","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1801.04726","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}