In this paper, we propose Latent Relation Language Models (LRLMs), a class of
language models that parameterizes the joint distribution over the words in a
document and the entities that occur therein via knowledge graph relations.
This model has a number of attractive properties: it not only improves language
modeling performance, but is also able to annotate the posterior probability of
entity spans for a given text through relations. Experiments demonstrate
empirical improvements over both a word-based baseline language model and a
previous approach that incorporates knowledge graph information. Qualitative
analysis further demonstrates the proposed model's ability to learn to predict
appropriate relations in context.

提出了一种基于知识图谱关系的潜在关系语言模型 (Latent Relation Language Models, LRLMs), 该模型不仅能提高语言建模性能，还能添加实体跨度的后验概率，实验结果表明该模型的性能优于基准模型和之前的知识图谱信息存在的模型，定性分析进一步证明了所提议的模型在上下文中预测适当的关系的能力。

潜在关系语言模型

Latent Relation Language Models

We introduce a general framework for several information extraction tasks
that share span representations using dynamically constructed span graphs. The
graphs are constructed by selecting the most confident entity spans and linking
these nodes with confidence-weighted relation types and coreferences. The
dynamic span graph allows coreference and relation type confidences to
propagate through the graph to iteratively refine the span representations.
This is unlike previous multi-task frameworks for information extraction in
which the only interaction between tasks is in the shared first-layer LSTM. Our
framework significantly outperforms the state-of-the-art on multiple
information extraction tasks across multiple datasets reflecting different
domains. We further observe that the span enumeration approach is good at
detecting nested span entities, with significant F1 score improvement on the
ACE dataset.

介绍了一个通用的框架，用于多个信息提取任务，共享动态构建的跨度图表示，该图由选择最可靠的实体跨度所构成，并使用置信度加权关系类型和共参考建立节点，从而实现共参考和关系类型置信度通过图传播迭代地细化跨度表示，与以前的多任务信息提取框架不同，我们的框架显著优于多个数据集上的多个信息提取任务的最新水平，涵盖了不同的领域。另外，我们观察到跨度枚举方法在检测嵌套跨距实体方面表现出色，在 ACE 数据集上 F1 分数显著提高。