Learning Named Entity Tagger using Domain-Specific Dictionary
Learning Named Entity Tagger using Domain-Specific Dictionary
复制标题
DOI：
10.18653/v1/d18-1230
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Jingbo Shang;Liyuan Liu;Xiang Ren;Xiaotao Gu;Teng Ren;Jiawei Han
中科院分区：
文献类型：
--
作者：
Jingbo Shang;Liyuan Liu;Xiang Ren;Xiaotao Gu;Teng Ren;Jiawei Han
深度神经模型的最新进展使我们能够构建可靠的命名实体识别（NER）系统，而无需手工制作特征。然而，这样的方法需要大量手动标记的训练数据。人们一直在努力用远程监督（与外部字典结合）取代人类注释，但生成的嘈杂标签对学习有效的神经模型构成了重大挑战。在这里，我们提出了两个神经模型，以适应嘈杂的远程监督的字典。首先，在传统的序列标签框架下，我们提出了一个修改的模糊CRF层来处理具有多个可能标签的令牌。在识别了远程监督中噪声标签的性质之后，我们超越了传统的框架，提出了一种新的、更有效的神经模型AutoNER，并采用了一种新的Tie or Break方案。此外，我们还讨论了如何完善远程监督，以获得更好的NER性能。在三个基准数据集上进行的大量实验表明，AutoNER在只使用字典而不需要额外的人工操作时实现了最佳性能，并在最先进的监督基准测试中提供了有竞争力的结果。
Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features. However, such methods require large amounts of manually-labeled training data. There have been efforts on replacing human annotations with distant supervision (in conjunction with external dictionaries), but the generated noisy labels pose significant challenges on learning effective neural models. Here we propose two neural models to suit noisy distant supervision from the dictionary. First, under the traditional sequence labeling framework, we propose a revised fuzzy CRF layer to handle tokens with multiple possible labels. After identifying the nature of noisy labels in distant supervision, we go beyond the traditional framework and propose a novel, more effective neural model AutoNER with a new Tie or Break scheme. In addition, we discuss how to refine distant supervision for better NER performance. Extensive experiments on three benchmark datasets demonstrate that AutoNER achieves the best performance when only using dictionaries with no additional human effort, and delivers competitive results with state-of-the-art supervised benchmarks.