Corpus ID: 53158404

Progressive Memory Banks for Incremental Domain Adaptation

@article{Asghar2020ProgressiveMB,
  title={Progressive Memory Banks for Incremental Domain Adaptation},
  author={Nabiha Asghar and Lili Mou and Kira A. Selby and Kevin D. Pantasdo and P. Poupart and Xin Jiang},
  journal={ArXiv},
  year={2020},
  volume={abs/1811.00239}
}
  • Nabiha Asghar, Lili Mou, +3 authors Xin Jiang
  • Published 2020
  • Computer Science
  • ArXiv
  • This paper addresses the problem of incremental domain adaptation (IDA) in natural language processing (NLP). We assume each domain comes one after another, and that we could only access data in the current domain. The goal of IDA is to build a unified model performing well on all the domains that we have encountered. We adopt the recurrent neural network (RNN) widely used in NLP, but augment it with a directly parameterized memory bank, which is retrieved by an attention mechanism at each step… CONTINUE READING
    7 Citations
    Continual Domain Adaptation for Machine Reading Comprehension
    • PDF
    Sequential Domain Adaptation through Elastic Weight Consolidation for Sentiment Analysis
    • 3
    • Highly Influenced
    • PDF
    Continual Learning with Gated Incremental Memories for sequential data processing
    • 3
    • PDF
    Continual Learning in Recurrent Neural Networks
    • PDF
    Emotion-Aware and Human-Like Autonomous Agents
    • 1
    Studying Catastrophic Forgetting in Neural Ranking Models
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 44 REFERENCES
    End-To-End Memory Networks
    • 1,621
    • PDF
    Sequence to Sequence Learning with Neural Networks
    • 11,464
    • PDF
    Overcoming Catastrophic Forgetting by Incremental Moment Matching
    • 242
    • Highly Influential
    • PDF
    Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
    • 138
    • PDF
    Domain-Adversarial Training of Neural Networks
    • 2,886
    • PDF
    Lifelong Learning with Dynamically Expandable Networks
    • 283
    • Highly Influential
    • PDF
    Learning without Forgetting
    • Zhizhong Li, Derek Hoiem
    • Computer Science, Mathematics
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2018
    • 857
    • PDF
    Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
    • 45
    • Highly Influential
    • PDF