论文标题
通过利用图形神经网络和二阶推断利用以实体为中心的特征来改善核心分辨率
Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference
论文作者
论文摘要
核心解决方案中的主要挑战之一是如何利用在提及群中定义的实体级特征而不是提及对。但是，核心提及通常在整个文本中分开较远，这使得纳入实体级特征非常困难。我们提出了一种基于图形神经网络的核心分辨率方法，该方法可以通过鼓励在所有可能指代相同现实世界实体的提及的功能共享中捕获以实体为中心的信息。提及通过边缘建模彼此链接，以指出两个链接的提及指向同一实体的可能性。通过此类图进行建模，提及之间的特征可以通过以实体方式传递操作来共享。还介绍了最高二阶特征的全局推断算法，以最佳的聚类提及一致的组。实验结果表明，我们的基于图形神经网络的方法与二阶解码算法（名为GNNCR）梳理，在英语Conll-2012共享任务数据集上达到了接近最新性能。
One of the major challenges in coreference resolution is how to make use of entity-level features defined over clusters of mentions rather than mention pairs. However, coreferent mentions usually spread far apart in an entire text, which makes it extremely difficult to incorporate entity-level features. We propose a graph neural network-based coreference resolution method that can capture the entity-centric information by encouraging the sharing of features across all mentions that probably refer to the same real-world entity. Mentions are linked to each other via the edges modeling how likely two linked mentions point to the same entity. Modeling by such graphs, the features between mentions can be shared by message passing operations in an entity-centric manner. A global inference algorithm up to second-order features is also presented to optimally cluster mentions into consistent groups. Experimental results show our graph neural network-based method combing with the second-order decoding algorithm (named GNNCR) achieved close to state-of-the-art performance on the English CoNLL-2012 Shared Task dataset.
