基于组合神经网络的语义省略“的”字结构识别

针对语义省略“的”字结构识别任务, 提出一种基于组合神经网络的识别方法。利用词语和词性, 通过双向LSTM (long short-term memory)神经网络, 学习“的”字结构深层次的语义语法表示。通过Max-pooling层和基于GRU(gated recurrent unit)的多注意力层, 捕获“的”字结构的省略特征, 完成语义省略“的”字结构识别任务。实验结果表明, 所提模型在CTB8.0(Chinese Treebank 8.0)语料中, 能够有效地识别语义省略的“的”字结构, F1值达到96.67%。

Hybrid Neural Network for Recognition of the “de” Structure with Semantic Ellipsis

To slove the classification of the “de” structure containing the usage of semantic ellipsis, a hybrid neural network is built. Firstly, the network uses a bidirectional LSTM (long short-term memory) neural network to learn more syntactic and semantic information of the “de” structure. Then, the network employs a Max-poolinglayer or GRU (gated recurrent unit) based multiple attention layers to capture features of ellipsis of the “de” structure by which the network can recognize the “de” structure containing the usage of semantic ellipsis. Experiments on CTB8.0 corpus show that the proposed approach can achieve accurate results efficiently, the F1 value is 96.67%.