论文标题
使用类型信息来改善实体核心分辨率
Using Type Information to Improve Entity Coreference Resolution
论文作者
论文摘要
核心分辨率（CR）是话语分析的重要组成部分。最近，已经提出了神经方法来改善早期范式的SOTA模型。到目前为止，尚无公开的神经模型利用外部语义知识，例如类型信息。本文提供了第一个这样的模型和评估，通过引入黄金标准或预测类型来证明准确性的适度提高。在拟议的方法中，类型信息既适用于（1）提高提及表示形式，并且（2）在Coreference候选者提及之间创建软类型的一致性检查。我们的评估涵盖了四个不同的基准语料库的两种不同类型的谷物尺寸。
Coreference resolution (CR) is an essential part of discourse analysis. Most recently, neural approaches have been proposed to improve over SOTA models from earlier paradigms. So far none of the published neural models leverage external semantic knowledge such as type information. This paper offers the first such model and evaluation, demonstrating modest gains in accuracy by introducing either gold standard or predicted types. In the proposed approach, type information serves both to (1) improve mention representation and (2) create a soft type consistency check between coreference candidate mentions. Our evaluation covers two different grain sizes of types over four different benchmark corpora.
