【目的】更加全面地提取文本語義特征,提高文本向量對文本語義的表示能力。【方法】通過卷積神經網絡提取詞粒度、主題粒度和字粒度文本特征向量,通過"融合門"機制將三種特征向量融合得到最終的文本向量,并進行文本分類實驗。【結果】該模型在搜狗語料庫文本分類實驗上的準確率為92.56%,查準率為92.33%,查全率為92.07%,F1值為92.20%,較基準模型Text-CNN分別提高2.40%,2.05%,1.77%,1.91%。【局限】詞序關系范圍較小,語料庫規模較小。【結論】該模型可以更加全面地提取文本語義特征,得到的文本向量對文本語義表示能力更強。

[Objective] This paper proposed a model to extract semantic features from texts more comprehensively and to improve the representation of semantics by text vectors. [Methods] We obtained the word-granularity, topic-granularity and character-granularity feature vectors with the help of convolutional neural networks. Then, the three feature vectors were combined by the "merging gate" mechanism to generate the final text vectors. Finally, we examined the model with text classification experiment. [Results] The accuracy(92.56%), the precision(92.33%), the recall(92.07%) and the F-score(92.20%), were 2.40%, 2.05%, 1.77% and 1.91% higher than the results of Text-CNN. [Limitations] The Long-distance dependency features need to be included and the corpus size needs to be expanded. [Conclusions] The proposed model could better represent the text semantics.