摘要
现有的论辩挖掘工作大多针对单个数据集建模,忽视数据集不同时可能存在的特征变化情况,导致模型的泛化性能较差.因此,文中提出基于多任务学习的论辩挖掘方法,将多个数据集的论辩挖掘任务进行联合学习.首先融合多个任务的输入层表示,通过卷积神经网络和高速神经网络获取词级别和字符级共享参数,联合任务相关特征输入栈式双向长短记忆网络,利用多个论辩挖掘任务之间的关联信息并行训练,最终由条件随机场得到序列标注结果.在6个不同领域的数据集上的实验表明,文中方法在Macro-F1值上有所提升,由此验证方法的有效性.
Most of the existing research on argumentation mining is focused on modeling single dataset,and the possible changes in feature of different datasets are neglected.And thus the generalization performance of the model is decreased.Therefore,an argumentation mining method based on multi-task learning is proposed to combine the argumentation mining tasks of multiple datasets for joint learning.Firstly,the input layers of multiple tasks are fused,and the sharing parameters of word level and character level are obtained via deep convolutional neural network and highway network.The joint task-related feature input into stacking long-short term memory is utilized to train the correlation information between multiple argumentation mining tasks in parallel.Finally,the results of sequence labeling are obtained by the conditional random field.The experimental results on six datasets of various fields verify the effectiveness of the proposed method with increased Macro-F1.
作者
廖祥文
倪继昌
魏晶晶
吴运兵
陈国龙
LIAO Xiangwen;NI Jichang;WEI Jingjing;WU Yunbing;CHEN Guolong(College of Mathematics and Computer Science,Fuzhou University,Fuzhou 350116;Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing,Fuzhou University,Fuzhou 350116;Digital Fujian Institute of Financial Big Data,Fuzhou 350116;College of Electronics and Information Science,Fujian Jiang-xia University,Fuzhou 350108)
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2019年第12期1072-1079,共8页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.61772135,U1605251)
福建省自然科学基金面上项目(No.2017J01755)
中国科学院网络数据科学与技术重点实验室开放基金课题(No.CASNDST201708,CASNDST201606)
模式识别国家重点实验室开放课题基金项目(No.201900041)
赛尔网络下一代互联网技术创新项目(No.NGII20160501)
北邮可信分布式计算与服务教育部重点实验室主任基金项目(No.2017KF01)~~
关键词
论辩挖掘
多任务学习
深度学习
神经网络
Argumentation Mining
Multi-task Learning
Deep Learning
Neural Network
