【目的】通過任務標簽嵌入方法改進注意力機制,學習特定任務信息并產生與任務相關的注意力權重,提高文本向量的表示能力。【方法】通過多層LSTM提取文本潛在語義的向量表示;通過標簽嵌入學習到不同標簽下最關注的單詞,獲取特定任務下的背景語義信息,并產生注意力權重;計算得到融合特定任務信息的文本表示向量,并用于文本的分類預測。【結果】相比TextCNN、BiGRU、TLSTM、LSTMAtt以及SelfAtt模型,本文方法在情感、主題、主客觀句、領域等多個數據集上的分類準確率提升0.60%～11.95%,總體平均提升5.27%,同時該模型具有收斂速度快、復雜度較低等優點。【局限】實驗數據集規模和任務類型相對有限,可進一步擴充進行模型驗證和優化。【結論】該模型具有面向任務、輕量級的特點,可有效提高文本語義的表達能力和分類效果,具有較強的實用價值。

[Objective] This study uses the Label Embedding technique to modify attention mechanism. It learns the task-specific information and generates task-related attention weights, aiming to improve the quality of text representation vectors. [Methods] First, we adopted Multi-level LSTM to extract potential semantic representation of texts. Then, we retrieved the words attracted most attention with different labels to generate attention weights through Label Embedding. Finally, we calculated the text representation vector with taskspecific information, which was used to predict text classification. [Results] Compared with the TextCNN,BiGRU, TLSTM, LSTMAtt, and SelfAtt models, performance of the proposed model on multiple datasets was improved by 0. 60% to 11.95%(with an overall average of 5.27%). It also had fast convergence speed and low complexity. [Limitations] The experimental datasets and the task-types need to be expanded. [Conclusions] The proposed model can effectively improve the classification results of text semantics, which has much practical value.