A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning
Abstract
Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. However, most previous works only consider simple or weak interactions, thereby failing to model complex correlations among three or more tasks. In this paper, we propose a multi-task learning architecture with four types of recurrent neural layers to fuse information across multiple related tasks. The architecture is structurally flexible and considers various interactions among tasks, which can be regarded as a generalized case of many previous works. Extensive experiments on five benchmark datasets for text classification show that our model can significantly improve performances of related tasks with additional information from others.
Cite
Text
Zhang et al. "A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/473Markdown
[Zhang et al. "A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/zhang2017ijcai-generalized/) doi:10.24963/IJCAI.2017/473BibTeX
@inproceedings{zhang2017ijcai-generalized,
title = {{A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning}},
author = {Zhang, Honglun and Xiao, Liqiang and Wang, Yongkun and Jin, Yaohui},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {3385-3391},
doi = {10.24963/IJCAI.2017/473},
url = {https://mlanthology.org/ijcai/2017/zhang2017ijcai-generalized/}
}