Previous studies have shown that there is potential semantic dependency between part-of-speech and semantic roles.At the same time,the predicate-argument structure in a sentence is important information for semantic r...Previous studies have shown that there is potential semantic dependency between part-of-speech and semantic roles.At the same time,the predicate-argument structure in a sentence is important information for semantic role labeling task.In this work,we introduce the auxiliary deep neural network model,which models semantic dependency between part-of-speech and semantic roles and incorporates the information of predicate-argument into semantic role labeling.Based on the framework of joint learning,part-of-speech tagging is used as an auxiliary task to improve the result of the semantic role labeling.In addition,we introduce the argument recognition layer in the training process of the main task-semantic role labeling,so the argument-related structural information selected by the predicate through the attention mechanism is used to assist the main task.Because the model makes full use of the semantic dependency between part-of-speech and semantic roles and the structural information of predicate-argument,our model achieved the F1 value of 89.0%on the WSJ test set of CoNLL2005,which is superior to existing state-of-the-art model about 0.8%.展开更多
现有的有监督可见光-近红外行人重识别方法需要大量人力资源去除手工标注数据,容易受到标注数据场景的限制,难以满足真实多变应用场景的泛化性。因此,文中提出基于语义伪标签和双重特征存储库的无监督跨模态行人重识别方法。首先,提出...现有的有监督可见光-近红外行人重识别方法需要大量人力资源去除手工标注数据,容易受到标注数据场景的限制,难以满足真实多变应用场景的泛化性。因此,文中提出基于语义伪标签和双重特征存储库的无监督跨模态行人重识别方法。首先,提出基于对比学习框架的预训练方法,利用可见光行人图像和其生成的辅助灰度图像进行训练。利用该预训练方法获取对颜色变化具有鲁棒性的语义特征提取网络。然后,使用DBSCAN(Density-Based Spatial Clustering of Applications with Noise)聚类方法生成语义伪标签。相比现有的伪标签生成方法,文中提出的语义伪标签在生成过程中充分利用跨模态数据之间的结构信息,减少跨模态数据颜色变化带来的模态差异。此外,文中还构建实例级困难样本特征存储库和中心级聚类特征存储库,充分利用困难样本特征和聚类特征,让模型对噪声伪标签具有更强的鲁棒性。在SYSU-MM01、RegDB两个跨模态数据集上的实验验证文中方法的有效性。展开更多
语义角色标注(Semantic Role Labeling,SRL)旨在识别给定句子中所包含的谓词及对应的语义论元,从而为信息抽取、自动问答和阅读理解等任务的语义理解提供帮助.构建句法特征作为实现语义角色标注任务的关键步骤,在很大程度上影响着任务...语义角色标注(Semantic Role Labeling,SRL)旨在识别给定句子中所包含的谓词及对应的语义论元,从而为信息抽取、自动问答和阅读理解等任务的语义理解提供帮助.构建句法特征作为实现语义角色标注任务的关键步骤,在很大程度上影响着任务的性能.针对现有的神经网络模型未能有效构建句法特征,例如现有研究采取离线式的人工定式句法裁剪方案,不可避免地造成关键句法信息丢失或者裁剪效果减弱等问题,本文提出基于动态句法剪枝机制的端到端神经网络模型,并将其用于中文语义角色标注任务.具体地,我们提出两种创新的动态句法剪枝机制:基于递归神经网络模型的动态句法剪枝机制(Recur-DSP)和基于带句法标签的图卷积网络模型的句法剪枝机制(SGCN-DSP).Recur-DSP采用递归神经网络模型进行句法结构编码与融合,并对句法树的每一个连接处通过Gumbel-Softmax函数离散化实现动态句法裁剪.SGCN-DSP采用图卷积神经网络模型为句法依存树的依存弧结构以及对应的标签进行统一建模,并提出对应的动态句法裁剪机制.在基准数据集上的实验结果显示所提方法超过当前的最好模型,获得当前中文语义角色标注的最优性能.通过整合预训练语言模型BERT,基于CoNLL09数据集,提出的模型SGCN-DSP在角色论元识别上获得了90.4%的F1值,在谓词识别上获得90.8%的F1值.展开更多
基金The work of this article is supported by Key Scientific Research Projects of Colleges and Universities in Henan Province(Grant No.20A520007)National Natural Science Foundation of China(Grant No.61402149).
文摘Previous studies have shown that there is potential semantic dependency between part-of-speech and semantic roles.At the same time,the predicate-argument structure in a sentence is important information for semantic role labeling task.In this work,we introduce the auxiliary deep neural network model,which models semantic dependency between part-of-speech and semantic roles and incorporates the information of predicate-argument into semantic role labeling.Based on the framework of joint learning,part-of-speech tagging is used as an auxiliary task to improve the result of the semantic role labeling.In addition,we introduce the argument recognition layer in the training process of the main task-semantic role labeling,so the argument-related structural information selected by the predicate through the attention mechanism is used to assist the main task.Because the model makes full use of the semantic dependency between part-of-speech and semantic roles and the structural information of predicate-argument,our model achieved the F1 value of 89.0%on the WSJ test set of CoNLL2005,which is superior to existing state-of-the-art model about 0.8%.
文摘现有的有监督可见光-近红外行人重识别方法需要大量人力资源去除手工标注数据,容易受到标注数据场景的限制,难以满足真实多变应用场景的泛化性。因此,文中提出基于语义伪标签和双重特征存储库的无监督跨模态行人重识别方法。首先,提出基于对比学习框架的预训练方法,利用可见光行人图像和其生成的辅助灰度图像进行训练。利用该预训练方法获取对颜色变化具有鲁棒性的语义特征提取网络。然后,使用DBSCAN(Density-Based Spatial Clustering of Applications with Noise)聚类方法生成语义伪标签。相比现有的伪标签生成方法,文中提出的语义伪标签在生成过程中充分利用跨模态数据之间的结构信息,减少跨模态数据颜色变化带来的模态差异。此外,文中还构建实例级困难样本特征存储库和中心级聚类特征存储库,充分利用困难样本特征和聚类特征,让模型对噪声伪标签具有更强的鲁棒性。在SYSU-MM01、RegDB两个跨模态数据集上的实验验证文中方法的有效性。
文摘语义角色标注(Semantic Role Labeling,SRL)旨在识别给定句子中所包含的谓词及对应的语义论元,从而为信息抽取、自动问答和阅读理解等任务的语义理解提供帮助.构建句法特征作为实现语义角色标注任务的关键步骤,在很大程度上影响着任务的性能.针对现有的神经网络模型未能有效构建句法特征,例如现有研究采取离线式的人工定式句法裁剪方案,不可避免地造成关键句法信息丢失或者裁剪效果减弱等问题,本文提出基于动态句法剪枝机制的端到端神经网络模型,并将其用于中文语义角色标注任务.具体地,我们提出两种创新的动态句法剪枝机制:基于递归神经网络模型的动态句法剪枝机制(Recur-DSP)和基于带句法标签的图卷积网络模型的句法剪枝机制(SGCN-DSP).Recur-DSP采用递归神经网络模型进行句法结构编码与融合,并对句法树的每一个连接处通过Gumbel-Softmax函数离散化实现动态句法裁剪.SGCN-DSP采用图卷积神经网络模型为句法依存树的依存弧结构以及对应的标签进行统一建模,并提出对应的动态句法裁剪机制.在基准数据集上的实验结果显示所提方法超过当前的最好模型,获得当前中文语义角色标注的最优性能.通过整合预训练语言模型BERT,基于CoNLL09数据集,提出的模型SGCN-DSP在角色论元识别上获得了90.4%的F1值,在谓词识别上获得90.8%的F1值.
