|
|||||
|
|
| 使用深度长短时记忆模型对于评价词和评价对象的联合抽取 | |
| 引用本文： | 沈亚田,黄萱菁,曹均阔. 使用深度长短时记忆模型对于评价词和评价对象的联合抽取[J]. 中文信息学报, 2018, 32(2): 110-119 |
| 作者姓名： | 沈亚田 黄萱菁 曹均阔 |
| 作者单位： | 1.复旦大学 计算机科学技术学院,上海 201203; 2.海南师范大学 信息科学技术学院,海南 海口 570100 |
| 基金项目： | 国家自然科学基金(61363032);海南省重大科技计划项目(ZDKJ2017012) |
| 摘 要： | 评价词和评价对象抽取在意见挖掘中是一个重要的任务,我们在句子级评价词和评价对象联合抽取任务上研究了长短时记忆(long short-term memory)神经网络模型的几种变种应用。长短时记忆神经网络模型是一种循环神经网络模型,该模型使用长短时记忆模型单元作为循环神经网络的记忆单元,它能够获得更多的长距离上下文信息,同时避免了普通循环神经网络的梯度消失和梯度爆炸的问题。我们对比了传统的方法,实验结果证明长短时记忆神经网络模型优于以前的方法,在细粒度评价词和评价对象的联合抽取中达到更好的性能。 |
| 关 键 词： | 循环神经网络 长短时记忆模型 评价词与评价对象联合抽取 深度学习 序列标注 |
Joint Extraction of Opinion Targets and Opinion Words Based on LSTM |
|
| SHEN Yatian,HUANG Xuanjing,CAO Junkuo. Joint Extraction of Opinion Targets and Opinion Words Based on LSTM[J]. Journal of Chinese Information Processing, 2018, 32(2): 110-119 | |
| Authors: | SHEN Yatian HUANG Xuanjing CAO Junkuo |
| Affiliation: | 1.School of Computer Science and Technolgy, Fudan University , Shanghai, 201203, China; 2.School of Information Science and Technology, Hainan Normal University, Haikou, Hainan 570100, China |
| Abstract: | To deal with opinion word and opinion target extraction, we explore several variants of long short-term memory recurrent neural networks for joint extraction of them at sentence-level. We also compare our models with previous classical approaches. The results of the experiments show that long short-term memory recurrent neural networks outperform previous baselines, achieving new state-of-the-art results for joint extraction of fine-grained opinion words and opinion targets. |
| Keywords: | recurrent neural networks long short-term memory model opinion words and target extraction deep learning sequence label |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |