A New Concept of Deep Reinforcement Learning based Augmented General Sequence Tagging System
This work addresses performance improvements in general sequence tagging for natural language understanding, but it appears incremental as it builds on existing deep learning and reinforcement learning methods.
The paper tackles the problem of sequence tagging in SLU and NLU tasks by proposing a deep reinforcement learning augmented system, which improves F1 scores by 1.9% on ATIS and 1.4% on CoNLL-2003 datasets compared to state-of-the-art models.
In this paper, a new deep reinforcement learning based augmented general sequence tagging system is proposed. The new system contains two parts: a deep neural network (DNN) based sequence tagging model and a deep reinforcement learning (DRL) based augmented tagger. The augmented tagger helps improve system performance by modeling the data with minority tags. The new system is evaluated on SLU and NLU sequence tagging tasks using ATIS and CoNLL-2003 benchmark datasets, to demonstrate the new system's outstanding performance on general tagging tasks. Evaluated by F1 scores, it shows that the new system outperforms the current state-of-the-art model on ATIS dataset by 1.9% and that on CoNLL-2003 dataset by 1.4%.