Identifying attack and support argumentative relations using deep learning
Identifying attack and support argumentative relations using deep learning
复制标题
DOI：
10.18653/v1/d17-1144
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
O. Cocarascu;Francesca Toni
中科院分区：
文献类型：
--
作者：
O. Cocarascu;Francesca Toni
我们提出了一种深度学习架构，以捕获从一段文本到另一段文本的攻击和支持的争论关系，这种关系在辩论中自然发生。该架构使用两个（单向或双向）长短期记忆网络和（训练或非训练）词嵌入，并允许大大改善现有的技术，使用相同形式的（基于关系的）参数挖掘的语法特征和监督分类器。
We propose a deep learning architecture to capture argumentative relations of attack and support from one piece of text to another, of the kind that naturally occur in a debate. The architecture uses two (unidirectional or bidirectional) Long Short-Term Memory networks and (trained or non-trained) word embeddings, and allows to considerably improve upon existing techniques that use syntactic features and supervised classifiers for the same form of (relation-based) argument mining.