Deep Multi-Task Learning with Shared Memory

2016/09/23 by Pengfei Liu, Xipeng Qiu, Liu, Pengfei +3
Computer Science · #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1609.07222

openalex publication_date 2016/09/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we propose two deep architectures which can be trained jointly on multiple related tasks. More specifically, we augment neural model with an external memory, which is shared by several tasks. Experiments on two groups of text classification tasks show that our proposed architectures can improve the performance of a task with the help of other related tasks.

Citations

• Long Short-Term Memory
• Finding Structure in Time
• Larger-Context Language Modelling
• Convolutional Neural Networks for Sentence Classification

Related

• Multi-Task Learning with Deep Neural Networks: A Survey
• Adversarial Multi-task Learning for Text Classification
• Recurrent Neural Network for Text Classification with Multi-Task Learning
• Exploring Shared Structures and Hierarchies for Multiple NLP Tasks
• A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning