An Encoder-Memory-Decoder Framework for Sub-Event Detection in Social Media | |
Guandan, Chen![]() ![]() ![]() | |
2018 | |
Conference Name | the 27th ACM International on Conference on Information and Knowledge Management |
Source Publication | Proceedings of the 27th ACM International on Conference on Information and Knowledge Management |
Conference Date | 2018.10.22-26 |
Conference Place | Lingotto, Turin, Italy |
Abstract | Sub-event detection can help faster and deeper understanding of an event by providing human-friendly clusters, and thus has become an important research topic in Web mining and knowledge management. In existing sub-event detection methods, clustering based methods are brittle for using heuristic similarity metric to judge whether documents belong to the same sub-event, while topic model based methods are limited to the bag of words assumption. To overcome these drawbacks in previous research, in this paper, we propose an encoder-memory-decoder framework for sub-event detection. Our model learns document and sub-event representations suitable for the similarity metric in a data-driven manner, and transforms sub-event detection into selecting the most proper sub-event representation that can maximize text reconstruction probability. Considering the case of overfitting, we also apply transfer learning in our model. To the best of our knowledge, our model is the first to develop an unsupervised deep neural model for sub-event detection. We use Twitter as an examplar social media platform for our study, and experimental results show that our model outperforms baseline methods for sub-event detection. |
Keyword | Encoder-memory-decoder Framework Sub-event Detection Deep Neural Network |
MOST Discipline Catalogue | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | https://doi.org/10.1145/3269206.3269256 |
URL | 查看原文 |
Indexed By | EI |
Funding Project | CAS Grant[ZDRW-XH-2017-3] ; NNSFC Innovative Team[71621002] ; MOST[2016QY02D0305] ; National Natural Science Foundation of China[71702182] ; National Natural Science Foundation of China[71702182] ; MOST[2016QY02D0305] ; NNSFC Innovative Team[71621002] ; CAS Grant[ZDRW-XH-2017-3] |
Language | 英语 |
Citation statistics | |
Document Type | 会议论文 |
Identifier | http://ir.ia.ac.cn/handle/173211/23613 |
Collection | 复杂系统管理与控制国家重点实验室_互联网大数据与信息安全 |
Affiliation | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
Recommended Citation GB/T 7714 | Guandan, Chen,Nan, Xu,Wenji, Mao. An Encoder-Memory-Decoder Framework for Sub-Event Detection in Social Media[C],2018. |
Files in This Item: | Download All | |||||
File Name/Size | DocType | Version | Access | License | ||
EMD-final.pdf(323KB) | 会议论文 | 开放获取 | CC BY-NC-SA | View Download |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment