论文标题
通过文档级交叉任务连贯奖励的联合语义分析
Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards
论文作者
论文摘要
核心分辨率和语义角色标签是捕获语义的不同方面的NLP任务，分别指示了同一实体的表达方式，以及句子中使用哪些语义角色表达式。但是，它们通常是紧密相互依存的，两者通常都需要自然的语言理解。它们是否形成文档的连贯抽象表示？我们提出了一种神经网络体系结构，用于英语的联合核心分辨率和语义角色标签，并提出了训练图神经网络，以建模合并浅的语义图的“连贯性”。使用由此产生的相干得分作为我们的联合语义分析仪的奖励，我们使用强化学习来鼓励对文档的全球连贯性以及语义注释之间。这导致了来自不同域的多个数据集中的两个任务的改进，以及各种表达性的编码器，我们认为，在NLP中使用更全面的语义方法。
Coreference resolution and semantic role labeling are NLP tasks that capture different aspects of semantics, indicating respectively, which expressions refer to the same entity, and what semantic roles expressions serve in the sentence. However, they are often closely interdependent, and both generally necessitate natural language understanding. Do they form a coherent abstract representation of documents? We present a neural network architecture for joint coreference resolution and semantic role labeling for English, and train graph neural networks to model the 'coherence' of the combined shallow semantic graph. Using the resulting coherence score as a reward for our joint semantic analyzer, we use reinforcement learning to encourage global coherence over the document and between semantic annotations. This leads to improvements on both tasks in multiple datasets from different domains, and across a range of encoders of different expressivity, calling, we believe, for a more holistic approach to semantics in NLP.
