基于Dropout正则化的汉语框架语义角色识别

Chinese FrameNet Semantic Role Identification Based on Dropout Regularization

汉语框架语义角色识别是汉语框架语义分析的重要任务之一。该文基于汉语词语、词性等特征的分布式表示,使用一种多特征融合的神经网络结构来构建汉语框架语义角色识别模型。鉴于可用的训练语料规模有限,该文采用了Dropout正则化技术来改进神经网络的训练过程。实验结果表明,Dropout正则化的加入有效地缓解了模型的过拟合现象,使得模型的F值有了近7%的提高。该文进一步优化了学习率以及分布式表示的初始值,最终的汉语框架语义角色识别的F值达到70.54%,较原有的最优结果提升2%左右。

Semantic role identification is an important task for semantic parsing according to Chinese FrameNet. Based on distributed representations of Chinese words, the part of-speech and other symbolic features, we build our semantic role identification model by employing a kind of multi-feature integrated neural network architecture. Due to the relative small training corpus, we adopt the dropout regularization to improve quality of the training process. Experimental results indicate that, 1） dropout regularization can effectively alleviate over-fitting of our model, and 2） the F-measure increases upto 7%. With further optimization of the learning rate and the pre-trained word embeddings, the final F-measure of our semantic role identification model reaches 70.54 %, which is about 2% higher than the state-of-the-art result.