arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1307.7973cs.CLcs.IRcs.LG
收藏

将语言和知识库与嵌入模型相结合用于关系抽取

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction

Google(谷歌);Heudiasyc UMR CNRS 7253(法国国家科学研究中心Heudiasyc混合研究单位7253);U. Tech. de Compiègne(贡比涅技术大学)

Jason Weston, Antoine Bordes, Oksana Yakhnenko, Nicolas Usunier

摘要:

本文提出了一种新的方法,关系抽取从自由文本,这是训练,以共同使用的信息,从文本和现有的知识。我们的模型是基于两个评分功能,通过学习低维嵌入的单词和实体和关系的知识库。我们在《纽约时报》与Freebase关系相关的文章中实证表明,我们的方法能够有效地使用Freebase数据的一个大子集(4M实体,23k关系)提供的额外信息,以改进现有的仅依赖文本特征的方法。

英文摘要:

This paper proposes a novel approach for relation extraction from free text which is trained to jointly use information from the text and from existing knowledge. Our model is based on two scoring functions that operate by learning low-dimensional embeddings of words and of entities and relationships from a knowledge base. We empirically show on New York Times articles aligned with Freebase relations that our approach is able to efficiently use the extra information provided by a large subset of Freebase data (4M entities, 23k relationships) to improve over existing methods that rely on text features alone.

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。

↑