论文标题
合并组成语法用于核心分辨率
Incorporating Constituent Syntax for Coreference Resolution
论文作者
论文摘要
语法已被证明可以使核心分辨率受益于在传统的基于统计机器学习的系统或最近提出的神经模型中捕获的远程依赖关系和结构化信息。但是，大多数领先的系统仅使用依赖树。我们认为，组成树还编码重要信息，例如由嵌套的多字短语捕获的显式跨界信号，额外的语言标签和层次结构，可用于检测图形。在这项工作中，我们提出了一种简单但有效的基于图的方法，以结合构成句法结构。此外，我们还探索以利用高阶邻里信息来编码组成树中的丰富结构。因此，提出了一种新的消息传播机制，以使语法树中元素之间的信息流在元素之间。对Ontonotes的英语和中国部分的实验5.0基准表明，我们提出的模型要么超过了强大的基线，要么实现了新的最新性能。 （代码可在https://github.com/fantabulou-j/coref-constituent-graph上获得）
Syntax has been shown to benefit Coreference Resolution from incorporating long-range dependencies and structured information captured by syntax trees, either in traditional statistical machine learning based systems or recently proposed neural models. However, most leading systems use only dependency trees. We argue that constituent trees also encode important information, such as explicit span-boundary signals captured by nested multi-word phrases, extra linguistic labels and hierarchical structures useful for detecting anaphora. In this work, we propose a simple yet effective graph-based method to incorporate constituent syntactic structures. Moreover, we also explore to utilise higher-order neighbourhood information to encode rich structures in constituent trees. A novel message propagation mechanism is therefore proposed to enable information flow among elements in syntax trees. Experiments on the English and Chinese portions of OntoNotes 5.0 benchmark show that our proposed model either beats a strong baseline or achieves new state-of-the-art performance. (Code is available at https://github.com/Fantabulous-J/Coref-Constituent-Graph)
