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 2106.04098cs.CL
收藏

基于屏蔽语言模型的弱监督超精细实体分类

Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model

HKUST(香港科技大学);Instacart(因斯塔卡特)

Hongliang Dai, Yangqiu Song, Haixun Wang

摘要:

最近,人们努力通过使用更丰富和超精细的类型集合来扩展细粒度的实体类型,并且标记包括代词和名词性名词的名词短语,而不仅仅是命名的实体提及。这种超精细实体分类任务的一个关键挑战是,人类注释的数据非常稀缺,现有的远程或弱监督方法的注释能力非常有限。为了解决这个问题,在本文中,我们建议通过使用BERT掩蔽语言模型(MLM)来获取用于超细实体分类的训练数据。给定一个句子中的提及,我们的方法为BERT MLM构造一个输入,以便它预测提及的上下文相关上位词,这些上位词可以用作类型标签。实验结果表明,在这些自动生成的标签的帮助下,超细实体分类模型的性能可以得到大幅提高。我们还表明,我们的方法可以应用于改进传统的细粒度实体类型执行简单的类型映射后。

英文摘要:

Recently, there is an effort to extend fine-grained entity typing by using a richer and ultra-fine set of types, and labeling noun phrases including pronouns and nominal nouns instead of just named entity mentions. A key challenge for this ultra-fine entity typing task is that human annotated data are extremely scarce, and the annotation ability of existing distant or weak supervision approaches is very limited. To remedy this problem, in this paper, we propose to obtain training data for ultra-fine entity typing by using a BERT Masked Language Model (MLM). Given a mention in a sentence, our approach constructs an input for the BERT MLM so that it predicts context dependent hypernyms of the mention, which can be used as type labels. Experimental results demonstrate that, with the help of these automatically generated labels, the performance of an ultra-fine entity typing model can be improved substantially. We also show that our approach can be applied to improve traditional fine-grained entity typing after performing simple type mapping.

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。

↑