In this paper we proposed the use of effective features and transfer leaning to improve the accuracies of neural-network-based models for accurate semantic role labeling (SRL) of Japanese, which is an aggregated language. We first reveal that the final morphemes in each argument, which have not been discussed in previous work on English SRL are effective features in determining semantic role labels in Japanese. We then discuss the possibility of using large-scale training corpora annotated with different semantic labels from the target semantic labels by transfer learning on CNN, 3-LNN, and GRU models. The experimental results of Japanese SRL on the proposed models indicate that all of the neural-network-based models performed better with transfer learning as well as using the feature vectors of final moprhemes in each argument.
展开▼
机译：在本文中，我们提出了使用有效特征和转移倾向来提高基于神经网络的模型的准确性，以准确地日语（一种聚合语言）的语义角色标记（SRL）。我们首先揭示出，每个参数中的最终语素（以前在英语SRL上没有讨论过）是确定日语中语义角色标签的有效特征。然后，我们讨论了通过在CNN，3-LNN和GRU模型上进行转移学习来使用标注有与目标语义标签不同的语义标签的大规模训练语料库的可能性。 Japanese SRL在提出的模型上的实验结果表明，所有基于神经网络的模型在转移学习以及在每个参数中使用最终词首的特征向量时都表现更好。
展开▼
