Learning Connective-based Word Representations for Implicit Discourse Relation Identification
Learning Connective-based Word Representations for Implicit Discourse Relation Identification
复制标题
DOI：
10.18653/v1/d16-1020
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Chloé Braud;P. Denis
中科院分区：
文献类型：
--
作者：
Chloé Braud;P. Denis
我们引入了一种简单的半监督方法来改进隐含话语关系识别。该方法利用大量自动提取的语篇连接词及其论元来构建新的分布词表征。具体地说，我们在语篇连接词空间中表示词，作为一种直接编码其修辞功能的方式。在宾夕法尼亚语篇树库上的实验表明，这些任务定制的表征在预测隐含语篇关系方面是有效的。我们的结果确实表明，尽管它们简单，但这些基于连接的表示法的性能优于各种现成的词嵌入，并在这个问题上取得了最先进的性能。
We introduce a simple semi-supervised approach to improve implicit discourse relation identification. This approach harnesses large amounts of automatically extracted discourse connectives along with their arguments to construct new distributional word representations. Specifically, we represent words in the space of discourse connectives as a way to directly encode their rhetorical function. Experiments on the Penn Discourse Treebank demonstrate the effectiveness of these task-tailored representations in predicting implicit discourse relations. Our results indeed show that, despite their simplicity, these connective-based representations outperform various off-the-shelf word embeddings, and achieve state-of-the-art performance on this problem.