Implicit Discourse Relation Recognition for English and Chinese with Multiview Modeling and Effective Representation Learning
Implicit Discourse Relation Recognition for English and Chinese with Multiview Modeling and Effective Representation Learning
复制标题
基于多视图建模和有效表征学习的英汉隐式话语关系识别
DOI：
10.1145/3028772
复制
发表时间：
2017-03
影响因子：
2
通讯作者：
Zong Chengqing
中科院分区：
文献类型：
--
作者：
Li Haoran;Zhang Jiajun;Zong Chengqing
两个文本片段之间的话语关系在许多自然语言处理（NLP）任务中起着重要作用。连接词强烈地指示了话语关系的意义，而事实上，在很大一部分话语关系中没有连接词，即隐性话语关系。与外显关系相比，内隐关系更难被发现，因而受到人们的广泛关注。到目前为止，对英语中隐性话语关系的研究已经很多，而对汉语中隐性话语关系识别的研究却很少，尽管汉语中的隐性话语关系比英语中的隐性话语关系更为普遍。在我们的工作中，英语和中文都是我们的重点。隐性关系预测的关键是对两个话语论元的语义以及它们之间的语境互动进行适当的建模。为了实现这一目标，我们提出了一个基于神经网络的框架，由两个层次。第一个是模型层次，在这个模型层次中，我们提出了一种最大边际学习方法来从多个角度探索隐含的话语关系。第二个是特征层次，在其中我们学习从词、论元、句法结构到句子的多级分布式表示。我们在英语和汉语标准测试集上进行了实验，结果表明，与几种方法相比，我们提出的方法在大多数情况下都能达到最佳的性能。
Discourse relations between two text segments play an important role in many Natural Language Processing (NLP) tasks. The connectives strongly indicate the sense of discourse relations, while in fact, there are no connectives in a large proportion of discourse relations, that is, implicit discourse relations. Compared with explicit relations, implicit relations are much harder to detect and have drawn significant attention. Until now, there have been many studies focusing on English implicit discourse relations, and few studies address implicit relation recognition in Chinese even though the implicit discourse relations in Chinese are more common than those in English. In our work, both the English and Chinese languages are our focus. The key to implicit relation prediction is to properly model the semantics of the two discourse arguments, as well as the contextual interaction between them. To achieve this goal, we propose a neural network based framework that consists of two hierarchies. The first one is the model hierarchy, in which we propose a max-margin learning method to explore the implicit discourse relation from multiple views. The second one is the feature hierarchy, in which we learn multilevel distributed representations from words, arguments, and syntactic structures to sentences. We have conducted experiments on the standard benchmarks of English and Chinese, and the results show that compared with several methods our proposed method can achieve the best performance in most cases.
登录
查看更多内容
DOI：
10.3115/1699510.1699555
发表时间：
2009-08
期刊：
--
影响因子：
--
作者：
Ziheng Lin;Min-Yen Kan;H. Ng
通讯作者：
Ziheng Lin;Min-Yen Kan;H. Ng
DOI：
--
发表时间：
2010-09
期刊：
--
影响因子：
--
作者：
Annie Louis;A. Joshi;R. Prasad;A. Nenkova
通讯作者：
Annie Louis;A. Joshi;R. Prasad;A. Nenkova
影响因子：
2.7
作者：
Yuping Zhou;Nianwen Xue
通讯作者：
Yuping Zhou;Nianwen Xue
DOI：
10.3115/v1/p14-1092
发表时间：
2014
期刊：
--
影响因子：
--
作者：
Peter Alexander Jansen;M. Surdeanu;Peter Clark
通讯作者：
Peter Alexander Jansen;M. Surdeanu;Peter Clark
影响因子：
2.7
作者：
Zhu, CY;Byrd, RH;Nocedal, J
通讯作者：
Nocedal, J