Search Results for author: Shihan Wang

Found 11 papers, 2 papers with code

Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy

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.

A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning

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.

Public Sentiment on Governmental COVID-19 Measures in Dutch Social Media

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.

Sentiment Analysis

Knowledge acquisition for dialogue agents using reinforcement learning on graph representations

no code implementations27 Jun 2024 Selene Baez Santamaria, Shihan Wang, Piek Vossen

We develop an artificial agent motivated to augment its knowledge base beyond its initial training.

Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks

no code implementations25 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.

reinforcement-learning Reinforcement Learning (RL)

Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization

no code implementations5 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.

Data Augmentation Efficient Exploration

Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions

no code implementations10 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.

Position reinforcement-learning +1

Dutch General Public Reaction on Governmental COVID-19 Measures and Announcements in Twitter Data

1 code implementation12 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.