论文标题
GNN-SL：基于GNN最近的示例的序列标记
GNN-SL: Sequence Labeling Based on Nearest Examples via GNN
论文作者
论文摘要
为了更好地处理序列标签（SL）任务中的长尾案例，在这项工作中，我们介绍了图形神经网络序列标签（GNN-SL），从而增强了Vanilla SL模型输出，并从整个训练集中检索出类似的标记示例。由于并非所有检索的标记示例都受益于模型预测，因此我们构建了一个异质图，并利用图形神经网络（GNN）来传输所检索的标记示例和输入单词序列之间的信息。从邻居中汇总信息的增强节点用于进行预测。该策略使该模型能够直接获得类似的标记示例并提高预测的一般质量。我们对三个典型序列标签任务进行了多种实验：命名实体识别（NER），语音标记的一部分（POS）和中文单词分割（CWS），以显示我们GNN-SL的显着性能。值得注意的是，GNN-SL在PKU上达到96.9（+0.2）的SOTA结果，在Cityu上达到98.3（+0.4），在MSR上达到98.5（+0.2），在96.9（+0.2）上，在CWS任务上与NER DataSets和posSotAsets and Poss和POSSETASES和POSSET and and POSS and as as as as as as as as as as as ass and POSSETS and and ass and as as as as as as as as as asset and and asset and and＆posseps anc。
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.
