arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.07690cs.CL
收藏

潜在关系语言模型

Latent Relation Language Models

Carnegie Mellon University(卡内基梅隆大学);Microsoft Research AI(微软研究院AI)

Hiroaki Hayashi, Zecong Hu, Chenyan Xiong, Graham Neubig

摘要:

在本文中,我们提出了潜在关系语言模型(LRLM),一类语言模型,参数化的联合分布在一个文档中的单词和实体,通过知识图谱的关系。该模型具有许多吸引人的特性:它不仅提高了语言建模性能,而且还能够通过关系注释给定文本的实体跨度的后验概率。实验表明,经验的改进基于单词的基线语言模型和以前的方法,结合知识图谱信息。定性分析进一步证明了所提出的模型的能力,学习预测适当的关系的背景。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑