一种面向生文本的事件同指消解神经网络方法

事件同指消解在自然语言理解中是一项复杂的任务,它需要在理解文本信息的基础上,发现其中的同指事件。事件同指消解在信息抽取、问答系统、阅读理解等自然语言任务中均有重要作用。该文提出了一个事件同指消解框架,包括事件抽取(ENS_NN)、真实性识别(ENS_NN)和事件同指消解(AGCNN)三个部分。事件同指消解模型(AGCNN)利用注意力池化机制来捕获事件的全局特征,利用门控卷积抽取复杂语义特征,提高了事件同指消解的性能。在KBP 2015和KBP 2016数据集上的实验结果表明,该文提出的方法优于目前最优的系统。

A Neural Method to Event Coreference Resolution in Raw Texts

Event coreference resolution is a complicated task in natural language understanding, which is to detect coreferential events in the text. This paper introduces a framework to resolve document-level event coreference, including the ENS_NN for event extraction and event realis detection, and the AGCNN for event coreference resolution. The AGCNN utilizes the attention pooling to capture global features in event sentences, and uses gated CNN to extract complicated semantic features, to improve performance of event coreference resolution. The experiments on the KBP2015 corpora and KBP2016 corpora show that our method achieves the state-of-the-art results.