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 2004.07493cs.CLcs.IRcs.LG
收藏

TriggerNER:使用实体触发器作为命名实体识别的解释进行学习

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition

University of Southern California(南加州大学);Amazon(亚马逊)

Bill Yuchen Lin, Dong-Ho Lee, Ming Shen, Ryan Moreno, Xiao Huang, Prashant Shiralkar, Xiang Ren

摘要:

在新领域中训练用于命名实体识别(NER)的神经模型通常需要额外的人类注释(例如,成千上万的标记实例),通常是昂贵的和耗时的收集。因此,一个关键的研究问题是如何获得监督在一个具有成本效益的方式。在本文中,我们引入了“实体触发器”,一个有效的代理人的解释,促进标签效率的学习NER模型。实体触发器被定义为句子中的一组单词,有助于解释为什么人类会识别句子中的实体。我们为两个经过充分研究的NER数据集众包了14k实体触发器。我们提出的模型,触发匹配网络,联合学习触发表示和软匹配模块与自我注意,这样就可以推广到看不见的句子很容易标记。我们的框架比传统的神经NER框架更具成本效益。实验表明,使用只有20%的注释者注释的句子的结果在一个相当的性能,使用70%的传统注释的句子。

英文摘要:

Training neural models for named entity recognition (NER) in a new domain often requires additional human annotations (e.g., tens of thousands of labeled instances) that are usually expensive and time-consuming to collect. Thus, a crucial research question is how to obtain supervision in a cost-effective way. In this paper, we introduce "entity triggers," an effective proxy of human explanations for facilitating label-efficient learning of NER models. An entity trigger is defined as a group of words in a sentence that helps to explain why humans would recognize an entity in the sentence. We crowd-sourced 14k entity triggers for two well-studied NER datasets. Our proposed model, Trigger Matching Network, jointly learns trigger representations and soft matching module with self-attention such that can generalize to unseen sentences easily for tagging. Our framework is significantly more cost-effective than the traditional neural NER frameworks. Experiments show that using only 20% of the trigger-annotated sentences results in a comparable performance as using 70% of conventional annotated sentences.

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。

↑