arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2202.13229cs.CLcs.AI
收藏

一种生成式关系抽取与分类模型

A Generative Model for Relation Extraction and Classification

IBM Research AI(IBM研究院人工智能部门)

Jian Ni, Gaetano Rossiello, Alfio Gliozzo, Radu Florian

摘要:

关系抽取是一项重要的信息抽取任务,它为知识库的扩充、问答等自然语言处理应用提供了必要的信息。在本文中,我们提出了一种新的生成模型的关系抽取和分类(我们称之为GREC),RE被建模为一个序列到序列的生成任务。我们探索各种编码表示的源和目标序列,并设计有效的方案,使GREC实现国家的最先进的性能在三个基准RE数据集。此外,我们引入负采样和解码缩放技术,提供了一个灵活的工具来调整模型的精度和召回性能。我们的方法可以扩展到从一个句子中提取所有的关系三元组。虽然一次通过的方法会导致一定的性能损失,但它在计算上更有效。

英文摘要:

Relation extraction (RE) is an important information extraction task which provides essential information to many NLP applications such as knowledge base population and question answering. In this paper, we present a novel generative model for relation extraction and classification (which we call GREC), where RE is modeled as a sequence-to-sequence generation task. We explore various encoding representations for the source and target sequences, and design effective schemes that enable GREC to achieve state-of-the-art performance on three benchmark RE datasets. In addition, we introduce negative sampling and decoding scaling techniques which provide a flexible tool to tune the precision and recall performance of the model. Our approach can be extended to extract all relation triples from a sentence in one pass. Although the one-pass approach incurs certain performance loss, it is much more computationally efficient.

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。

↑