| 基于注意力机制的双向长短时记忆网络模型突发事件演化关系抽取 |
| |
| 引用本文： | 闻畅,刘宇,顾进广. 基于注意力机制的双向长短时记忆网络模型突发事件演化关系抽取[J]. 计算机应用, 2019, 39(6): 1646-1651. DOI: 10.11772/j.issn.1001-9081.2018122533 |
| |
| 作者姓名： | 闻畅 刘宇 顾进广 |
| |
| 作者单位： | 武汉科技大学计算机科学与技术学院,武汉430065;智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学),武汉430065;武汉科技大学大数据科学与工程研究院,武汉430065;国家新闻出版署富媒体数字出版内容组织与知识服务重点实验室,北京100038;武汉科技大学计算机科学与技术学院,武汉430065;智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学),武汉430065;武汉科技大学大数据科学与工程研究院,武汉430065;国家新闻出版署富媒体数字出版内容组织与知识服务重点实验室,北京100038;武汉科技大学计算机科学与技术学院,武汉430065;智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学),武汉430065;武汉科技大学大数据科学与工程研究院,武汉430065;国家新闻出版署富媒体数字出版内容组织与知识服务重点实验室,北京100038 |
| |
| 基金项目： | 国家自然科学基金资助项目（61673304）；国家社会科学基金重大计划项目（11&ZD189）。 |
| |
| 摘 要： | 针对现有突发事件关系抽取研究多集中于因果关系抽取而忽略了其他演化关系的问题,为了提高应急决策中信息抽取的完备性,应用一种基于注意力机制的双向长短时记忆(LSTM)网络模型进行突发事件演化关系抽取。首先,结合突发事件演化关系的概念,构建演化关系模型并进行形式化定义,依据模型对突发事件语料进行标注;其次,搭建双向LSTM网络结构,并引入注意力机制计算注意力概率以突出关键词汇在文本中的重要程度;最终,使用搭建的网络模型进行演化关系抽取得到结果。在演化关系抽取实验中,相对于现有因果关系抽取方法,所提方法不仅抽取出更加充分的演化关系,为突发事件应急决策提供了更完善的信息;同时,在正确率、召回率和F1分数上分别平均提升了7.3%、6.7%和7.0%,有效提高了突发事件演化关系抽取的准确性。
|
| 关 键 词： | 关系抽取 突发事件 演化关系 注意力机制 双向长短时记忆网络 |
| 收稿时间： | 2018-12-24 |
| 修稿时间： | 2019-03-10 |
Evolution relationship extraction of emergency based on attention-based bidirectional long short-term memory network model |
| |
| WEN Chang,LIU Yu,GU Jinguang. Evolution relationship extraction of emergency based on attention-based bidirectional long short-term memory network model[J]. Journal of Computer Applications, 2019, 39(6): 1646-1651. DOI: 10.11772/j.issn.1001-9081.2018122533 |
| |
| Authors: | WEN Chang LIU Yu GU Jinguang |
| |
| Affiliation: | (Wuhan University of Science and Technology),Wuhan Hubei 430065,China;Key Laboratory of Intelligent Information Processing and Real-time Industrial System in Hubei Province(Wuhan University of Science and Technology),Wuhan Hubei 430065,China;Institute of Big Data Science and Engineering,Wuhan University of Science and Technology,Wuhan Hubei 430065,China;Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content,National Press and Publication Administration,Beijing 100038,China) |
| |
| Abstract: | Concerning the problem that existing study of emergency relationship extraction mostly focuses on causality extraction while neglects other evolutions, in order to improve the completeness of information extracted in emergency decision-making, a method based on attention-based bidirectional Long Short-Term Memory (LSTM) model was used to extract the evolution relationship. Firstly, combined with the concept of evolution relationship in emergencies, an evolution relationship model was constructed and given the formal definition, and the emergency corpus was labeled according to the model. Then, a bidirectional LSTM network was built and attention mechanism was introduced to calculate the attention probability to highlight the importance of the key words in the text. Finally, the built network model was used to extract the evolution relationship. In the evolution relationship extraction experiments, compared with the existing causality extraction methods, the proposed method can extract more sufficient evolution relationship for emergency decision-making. At the same time, the average precision, recall and F1_score are respectively increased by 7.3%, 6.7% and 7.0%, which effectively improves the accuracy of the evolution relationship extraction of emergency. |
| |
| Keywords: | relationship extraction emergency evolutionary relation attention mechanism bidirectional Long Short-Term Memory (LSTM) |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
|
