TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
复制标题
DOI：
10.18653/v1/2020.acl-main.752
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Bill Yuchen Lin;Dong-Ho Lee;Minghan Shen;Ryan Rene Moreno;Xiao Huang;Prashant Shiralkar;Xiang Ren
中科院分区：
文献类型：
--
作者：
Bill Yuchen Lin;Dong-Ho Lee;Minghan Shen;Ryan Rene Moreno;Xiao Huang;Prashant Shiralkar;Xiang Ren
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工注释（例如，数以万计的标记实例），而收集这些注释通常既昂贵又耗时。因此，一个关键的研究问题是如何以成本有效的方式获得监管。在本文中，我们介绍了“实体触发器”，它是人类解释的有效代理，可促进 NER 模型的标签高效学习。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 个实体触发器。我们提出的模型“触发匹配网络”联合学习触发表示和具有自注意力的软匹配模块，以便可以轻松泛化到未见过的句子以进行标记。我们的框架比传统的神经 NER 框架更具成本效益。实验表明，仅使用 20% 的触发注释句子所产生的性能与使用 70% 的传统注释句子的性能相当。
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.