学术报告

当前位置: 首页 > 新闻公告 > 学术报告 > 正文

学术报告预告:Encoding Relation Requirements for Relation Extraction via Joint Inference - 2014年ACL论文

发布时间: 2014-12-18     作者:马帅    点击次数:

报告题目:Encoding Relation Requirements for Relation Extraction via Joint Inference - 2014年ACL论文

时间:12月19日 周五 下午4:10

地点:北航新主楼H1018会议室

报告摘要: Most existing relation extraction models make predictions for each entity pair locally and individually, while ignoring implicit global clues available in the knowledge base, sometimes leading to conflicts among local predictions from different entity pairs. We therefore propose a joint inference framework that utilizes these global clues to resolve disagreements among local predictions. We exploit two kinds of clues to generate constraints which can capture the implicit type and cardinality requirements of a relation. Experimental results on three datasets, in both English and Chinese, show that our framework outperforms the state-of-the-art relation extraction models when such clues are applicable to the datasets. And, we find that the clues learnt automatically from existing knowledge bases perform comparably to those refined by human.

讲者介绍:Dr. Yansong Feng a Lecturer (Assistant Professor) in the Institute of Computer Science and Technology at Peking University, working with the group of Web Information Processing. Before that, he worked with Prof. Mirella Lapata and obtained my PhD from the School of Informatics at the University of Edinburgh.

(文/北航新闻网 摄影/无)
编辑:周洁