.png){kind=icon}
.png){kind=icon}
Return
Hierarchical Sequence-to-Sequence Model for Multi-Label Text Classification
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2948855.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose a novel sequence-to-sequence model for multi-label text classification, based on a parallel encoding, serial decoding strategy. The model combines a convolutional neural network and self-attention in parallel as the encoder to extract fine-grained local neighborhood information and global interaction information from the source text. We design a hierarchical decoder to decode and generate the label sequence. Our method not only gives full consideration to the interpretable fine-gained information in the source text but also effectively utilizes the information to generate the label sequence. We conducted a large number of comparative experiments on three datasets. The results show that the proposed model has significant advantages over the state-of-the-art baseline model. In addition, our analysis demonstrates that our model is competitive with the RNN-based Seq2Seq models and that it is more robust at handling datasets with a high label/sample ratio.
Keywords:
Decoding
Task analysis
Data mining
Convolution
Neural networks
Encoding
Analytical models
Sequence-to-sequence
multi-label text classification
self-attention
hierarchical decoder
attention mechanism
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.