NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback

2021-10-05 · Ruijie Zhou, Soham Deshmukh, Jeremiah Greer, Charles Lee

Current research in dialogue systems is focused on conversational assistants working on short conversations in either task-oriented or open domain settings. In this paper, we focus on improving task-based conversational assistants online, primarily those working on document-type conversations (e.g., emails) whose contents may or may not be completely related to the assistant's task. We propose "NARLE" a deep reinforcement learning (RL) framework for improving the natural language understanding (NLU) component of dialogue systems online without the need to collect human labels for customer data. The proposed solution associates user emotion with the assistant's action and uses that to improve NLU models using policy gradients. For two intent classification problems, we empirically show that using reinforcement learning to fine tune the pre-trained supervised learning models improves performance up to 43%. Furthermore, we demonstrate the robustness of the method to partial and noisy implicit feedback.

📄 PDF Abstract BibTeX arXiv:2110.02148

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningintent-classification Intent Classification Natural Language Understanding reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Ensnarled: On the topological linkage of spatially embedded network pairs

2022-08-24 · Felix Kramer, Carl D Modes

The observation, design and analysis of mesh-like networks in bionics, polymer physics and biological systems has brought forward an extensive catalog of fascinating structures of which a subgroup share a particular, yet…

Attribute

EmoFeedback$^2$: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback

2025-11-25 · Jingyang Jia, Kai Shu, Gang Yang, Long Xing 외 arxiv

Continuous emotional image content generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions and continuous emotional values. However, existing approaches lack emoti…

Image Generation

Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement Learning

2026-03-16 · Jing Ye, Xinpei Zhao, Lu Xiang, Yaping Zhang 외 arxiv

While current emotional support dialogue systems typically rely on expert-defined scalar rewards for alignment, these signals suffer from severe information sparsity. They cannot explain why a response failed or how to a…

Reinforcement Learning

Facial Expression Generation Aligned with Human Preference for Natural Dyadic Interaction

2026-03-07 · Xu Chen, Rui Gao, Xinjie Zhang, Haoyu Zhang 외 arxiv

Achieving natural dyadic interaction requires generating facial expressions that are emotionally appropriate and socially aligned with human preference. Human feedback offers a compelling mechanism to guide such alignmen…

Reinforcement Learning

Influencing Reinforcement Learning through Natural Language Guidance

2021-04-04 · Tasmia Tasrin, Md Sultan Al Nahian, Habarakadage Perera, Brent Harrison

Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that is either positive or negative. Whi…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)