SLShuyu Lei

Shuyu Lei

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shuyu Lei has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Task-Oriented Clustering for Dialogues

    by Chenxu Lv, Hengtong Lu, Shuyu Lei, Huixing Jiang, Wei Wu, Caixia Yuan, Xiaojie Wang

    Chenxu Lv, Hengtong Lu, Shuyu Lei, Huixing Jiang, Wei Wu, Caixia Yuan, Xiaojie Wang. Findings of the Association for Computational Linguistics: EMNLP 2021. 2021.

  • Open Access

    Slot Transferability for Cross-domain Slot Filling

    by Hengtong Lu, Zhuoxin Han, Caixia Yuan, Xiaojie Wang, Shuyu Lei, Huixing Jiang, Wei Wu

    Hengtong Lu, Zhuoxin Han, Caixia Yuan, Xiaojie Wang, Shuyu Lei, Huixing Jiang, Wei Wu. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.


  • Open Access

    Cooperative Multi-Agent Reinforcement Learning with Conversation Knowledge for Dialogue Management

    by Shuyu Lei, Xiaojie Wang, Caixia Yuan

    Dialogue management plays a vital role in task-oriented dialogue systems, which has become an active area of research in recent years. Despite the promising results brought from deep reinforcement learning, most of the studies need to develop a manual user simulator additionally. To address the time-consuming development of simulator policy, we propose a multi-agent dialogue model where an end-to-end dialogue manager and a user simulator are optimized simultaneously. Different from prior work, we optimize the two-agents from scratch and apply the reward shaping technology based on adjacency pairs constraints in conversational analysis to speed up learning and to avoid the derivation from normal human-human conversation. In addition, we generalize the one-to-one learning strategy to one-to-many learning strategy, where a dialogue manager can be concurrently optimized with various user simulators, to improve the performance of trained dialogue manager. The experimental results show that one-to-one agents trained with adjacency pairs constraints can converge faster and avoid derivation. In cross-model evaluation with human users involved, the dialogue manager trained in one-to-many strategy achieves the best performance.


  • Open Access

    Word-Based POMDP Dialog Management via Hybrid Learning

    by Shuyu Lei, Xiaojie Wang, Caixia Yuan

    Dialogue management plays an important role in the task-oriented dialogue system. Most of the previous work divide dialogue management into state tracker and action selector. The two parts are modeled separately and implemented in a pipeline way, which suffers from the problem of error accumulation, and the feedback signal from action selector cannot be propagated to state tracker and natural language understanding module. This paper proposes a word-based partially observable markov decision processes dialogue management that integrates natural language understanding, state tracker, and action selector into an end-to-end architecture. Our proposed dialogue management takes the words from user utterances as inputs, and then produces optimal action as well as slot values of natural language understanding which are necessary for response generation. To this end, we propose a hybrid learning method, which integrates reinforcement learning and supervised learning, to optimize the action selector and slot filler jointly. In addition, we develop a high-return prioritized experience replay to speed up the convergence of the training process. Experimental results show that the proposed dialogue management outperforms four strong baselines in a series of different dialogue tasks. A human users evaluation also shows the same results. The high-return prioritized experience replay accelerates the convergence effectively, especially in the scenario that proposed dialogue management works on more complex tasks.