GNN-SL：基于最近实例的序列标记方法（GNN）
GNN-SL: Sequence Labeling Based on Nearest Examples via GNN
摘要：
为了更好地处理序列标记（SL）任务中的长尾情况，在这项工作中，我们引入了图神经网络序列标记（GNN-SL），它通过从整个训练集中检索到的相似标记示例来增强香草SL模型输出。由于并非所有检索到的标注示例都有利于模型预测，因此我们构建了一个异构图，并利用图神经网络（GNNs）在检索到的标注示例和输入单词序列之间传递信息。增强节点聚合来自邻居的信息来进行预测。该策略使模型能够直接获取相似的标记示例，并提高了预测的总体质量。我们在三个典型的序列标记任务上进行了各种实验：命名实体识别（NER），词性标注（POS）和中文分词（CWS），以显示我们的GNN-SL的显着性能。值得注意的是，GNN-SL在PKU上实现了96.9（+0.2）的SOTA结果，在CITYU上实现了98.3（+0.4），在MSR上实现了98.5（+0.2），在AS上实现了96.9（+0.2）的CWS任务，并且结果与NER数据集和POS数据集上的SOTA性能相当。
英文摘要：
To better handle long-tail cases in the sequence labeling (SL) task, in this work, we introduce graph neural networks sequence labeling (GNN-SL), which augments the vanilla SL model output with similar tagging examples retrieved from the whole training set. Since not all the retrieved tagging examples benefit the model prediction, we construct a heterogeneous graph, and leverage graph neural networks (GNNs) to transfer information between the retrieved tagging examples and the input word sequence. The augmented node which aggregates information from neighbors is used to do prediction. This strategy enables the model to directly acquire similar tagging examples and improves the general quality of predictions. We conduct a variety of experiments on three typical sequence labeling tasks: Named Entity Recognition (NER), Part of Speech Tagging (POS), and Chinese Word Segmentation (CWS) to show the significant performance of our GNN-SL. Notably, GNN-SL achieves SOTA results of 96.9 (+0.2) on PKU, 98.3 (+0.4) on CITYU, 98.5 (+0.2) on MSR, and 96.9 (+0.2) on AS for the CWS task, and results comparable to SOTA performances on NER datasets, and POS datasets.
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。
