A Multi-task Text Classification Model Based on Label Embedding Learning

Different text classification tasks have specific task features and the performance of text classification algorithm is highly affected by these task-specific features. It is crucial for text classification algorithms to extract task-specific features and thus improve the performance of text classification in different text classification tasks. The existing text classification algorithms use the attention-based neural network models to capture contextualized semantic features while ignores the task-specific features. In this paper, a text classification algorithm based on label-improved attention mechanism is proposed by integrating both contextualized semantic and task-specific features. Through label embedding to learn both word vector and modified-TF-IDF matrix, the task-specific features can be extracted and then attention weights are assigned to different words according to the extracted features, so as to improve the effectiveness of the attention-based neural network models on text classification. Experiments are carried on three text classification task data sets to verify the performance of the proposed method, including a six-category question classification data set, a two-category user comment data set, and a five-category sentiment data set. Results show that the proposed method has an average increase of 3.02% and 5.85% in F1 value compared with the existing LSTMAtt and SelfAtt models.