Bring you to the past: Automatic Generation of Topically Relevant Event Chronicles

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 575–585, Beijing, China, July 26-31, 2015. c⃝2015 Association for Computational Linguistics Bring you to the past: Automatic Generation of Topically Relevant Event Chronicles Tao Ge1,2, Wenzhe Pei1, Heng Ji3, Sujian Li1,2, Baobao Chang1,2, Zhifang Sui1,2 1Key Laboratory of Computational Linguistics, Ministry of Education, School of EECS, Peking University, Beijing, 100871, China 2Collaborative Innovation Center for Language Ability, Xuzhou, Jiangsu, 221009, China 3Computer Science Department, Rensselaer Polytechnic Institute, Troy, NY 12180, USA getao@pku.edu.cn, wenzhepei@pku.edu.cn, jih@rpi.edu, lisujian@pku.edu.cn, chbb@pku.edu.cn, szf@pku.edu.cn Abstract An event chronicle provides people with an easy and fast access to learn the past. In this paper, we propose the first novel approach to automatically generate a top- ically relevant event chronicle during a certain period given a reference chronicle during another period. Our approach con- sists of two core components – a time- aware hierarchical Bayesian model for event detection, and a learning-to-rank model to select the salient events to con- struct the final chronicle. Experimental re- sults demonstrate our approach is promis- ing to tackle this new problem. 1 Introduction Human civilization has developed for thousands of years. During the long period, history witnessed the changes of societies and dynasties, the revo- lution of science and technology, as well as the emergency of celebrities, which are great wealth for later generations. Even nowadays, people usu- ally look back through history either for their work or interests. Among various ways to learn history, many people prefer reading an event chronicle summarizing important events in the past, which saves much time and efforts. The left part of Figure 1 shows a disaster event chronicle from Infoplease1, by which people can easily learn important disaster events in 2009. Un- fortunately, almost all the available event chron- icles are created and edited manually, which re- quires editors to learn everything that happened in the past. Even if an editor tries her best to gener- ate an event chronicle, she still cannot guarantee that all the important events are included. More- over, when new events happen in the future, she 1http://www.infoplease.com/world/disasters/2009.html needs to update the chronicle in time, which is laborious. For example, the event chronicle of 2010 in Wikipedia2 has been edited 8,488 times by 3,211 distinct editors since this page was cre- ated. In addition, event chronicles can vary ac- cording to topic preferences. Some event chroni- cles are mainly about disasters while others may focus more on sports. For people interested in sports, the event chronicle in Figure 1 is unde- sirable. Due to the diversity of event chronicles, it is common that an event chronicle regarding a specific topic for some certain period is unavail- able. If editing an event chronicle can be done by computers, people can have an overview of any pe- riod according to their interests and do not have to wait for human editing, which will largely speed up knowledge acquisition and popularization. …

Content truncated to 500 words