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 2009.07317cs.CL
收藏

用于更好的细粒度命名实体识别的级联模型

Cascaded Models for Better Fine-Grained Named Entity Recognition

IBM Research AI(IBM研究院人工智能)

Parul Awasthy, Taesun Moon, Jian Ni, Radu Florian

摘要:

命名实体识别(Named Entity Recognition,NER)是许多自然语言应用(如关系抽取或事件抽取)的基础任务。大部分NER研究都是在具有少数实体类型的数据集上进行的(例如PER,ESTA,ORG,MISC),但许多现实世界的应用(灾难救援,复杂事件提取,执法)可以从更大的NER类型中受益。最近,创建了具有数百到数千种类型的实体的数据集,从而引发了新的研究方向(Sekine,2008;Ling和Weld,2012; Gillick等人,2014; Choiet al.,2018年)。在本文中,我们提出了一种标记细粒度NER的级联方法,适用于TAC KBP 2019评估中使用的新发布的细粒度NER数据集(Ji等人,2019),其灵感来自于训练数据可用于一些粗略标签的事实。使用组合的Transformer网络,我们表明,性能可以提高约20 F1的绝对值,与直接的模型建立在完整的细粒度类型相比,并显示,令人惊讶的是,使用课程标记的数据在三种语言导致英语数据的改善。

英文摘要:

Named Entity Recognition (NER) is an essential precursor task for many natural language applications, such as relation extraction or event extraction. Much of the NER research has been done on datasets with few classes of entity types (e.g. PER, LOC, ORG, MISC), but many real world applications (disaster relief, complex event extraction, law enforcement) can benefit from a larger NER typeset. More recently, datasets were created that have hundreds to thousands of types of entities, sparking new lines of research (Sekine, 2008;Ling and Weld, 2012; Gillick et al., 2014; Choiet al., 2018). In this paper we present a cascaded approach to labeling fine-grained NER, applying to a newly released fine-grained NER dataset that was used in the TAC KBP 2019 evaluation (Ji et al., 2019), inspired by the fact that training data is available for some of the coarse labels. Using a combination of transformer networks, we show that performance can be improved by about 20 F1 absolute, as compared with the straightforward model built on the full fine-grained types, and show that, surprisingly, using course-labeled data in three languages leads to an improvement in the English data.

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。

↑