no code implementations • EMNLP 2021 • Yangyang Zhao, Zhenyu Wang, Changxi Zhu, Shihan Wang
Most of the existing dialogue policy methods rely on a single learning system, while the human brain has two specialized learning and memory systems, supporting to find good solutions without requiring copious examples.
no code implementations • Findings (NAACL) 2022 • Yang Zhao, Hua Qin, Wang Zhenyu, Changxi Zhu, Shihan Wang
It supports evaluating the difficulty of dialogue tasks only using the learning experiences of dialogue policy and skip-level selection according to their learning needs to maximize the learning efficiency.
no code implementations • EMNLP (NLP-COVID19) 2020 • Shihan Wang, Marijn Schraagen, Erik Tjong Kim Sang, Mehdi Dastani
Public sentiment (the opinion, attitude or feeling that the public expresses) is a factor of interest for government, as it directly influences the implementation of policies.
no code implementations • 25 Jan 2024 • Shuai Han, Mehdi Dastani, Shihan Wang
In this work, we propose an RL algorithm that can automatically structure the reward function for sample efficiency, given a set of labels that signify subtasks.
no code implementations • 5 May 2023 • Yangyang Zhao, Zhenyu Wang, Mehdi Dastani, Shihan Wang
When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn.
no code implementations • 16 Mar 2022 • Changxi Zhu, Mehdi Dastani, Shihan Wang
Communication is an effective mechanism for coordinating the behavior of multiple agents.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 10 Mar 2021 • Chao Zhang, Shihan Wang, Henk Aarts, Mehdi Dastani
Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well.
no code implementations • COLING 2020 • Bin Jiang, Jing Hou, Wanyue Zhou, Chao Yang, Shihan Wang, Liang Pang
Aspect-based sentiment analysis (ABSA) aims to determine the sentiment polarity of each specific aspect in a given sentence.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • COLING 2020 • Bin Jiang, Wanyue Zhou, Jingxu Yang, Chao Yang, Shihan Wang, Liang Pang
However, generating personalized responses is still a challenging task since the leverage of predefined persona information is often insufficient.
1 code implementation • 12 Jun 2020 • Shihan Wang, Marijn Schraagen, Erik Tjong Kim Sang, Mehdi Dastani
Given the unprecedented nature of the COVID-19 crisis, having an up-to-date representation of public sentiment on governmental measures and announcements is crucial.