{"type":"ScholarlyArticle","title":"Taking Up the Gaokao Challenge: An Information Retrieval Approach","authors":[{"name":"Gong Cheng","slug":"gong-cheng","given":"Gong","family":"Cheng","affiliation":""},{"name":"Weixi Zhu","slug":"weixi-zhu","given":"Weixi","family":"Zhu","affiliation":""},{"name":"Ziwei Wang","slug":"ziwei-wang","given":"Ziwei","family":"Wang","affiliation":""},{"name":"Jianghui Chen","slug":"jianghui-chen","given":"Jianghui","family":"Chen","affiliation":""},{"name":"Yuzhong Qu","slug":"yuzhong-qu","given":"Yuzhong","family":"Qu","affiliation":""}],"abstract":"Answering questions in a university's entrance examination like Gaokao in China challenges AI technology. As a preliminary attempt to take up this challenge, we focus on multiple-choice questions in Gaokao, and propose a three-stage approach that exploits and extends information retrieval techniques. Taking Wikipedia as the source of knowledge, our approach obtains knowledge relevant to a question by retrieving pages from Wikipedia via string matching and context-based disambiguation, and then ranks and filters pages using multiple strategies to draw critical evidence, based on which the truth of each option is assessed via relevance-based entailment. It achieves encouraging results on real-life questions in recent history tests, significantly outperforming baseline approaches.","doi":null,"url":"https://ijcai.org/proceedings/2016/353","pdf":"https://ijcai.org/proceedings/2016/0353.pdf","markdown":"https://ijcai.org/proceedings/2016/353.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/353","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":353,"pages":{"first":2479,"last":2484},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}