Sentiment Adaptive End-to-End Dialog Systems

By Weiyan Shi, Zhou Yu. 2018

83 citations recorded by the source corpus.

End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating. However, current end-to-end approaches only consider user semantic inputs in learning and under-utilize other user information. Therefore, we propose to include user sentiment obtained through multimodal information (acoustic, dialogic and textual), in the end-to-end learning framework to make systems more user-adaptive and effective. We incorporated user sentiment information in both supervised and reinforcement learning settings. In both settings, adding sentiment information reduced the dialog length and improved the task success rate on a bus information search task. This work is the first attempt to incorporate multimodal user information in the adaptive end-to-end dialog system training framework and attained state-of-the-art performance.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog (2019, background): “[54]), but sometimes with more implicit signals, such as the user interrupting the system or starting over [55].”
Human-centric Dialog Training via Offline Reinforcement Learning (2020, background): “Some of these approaches incorporate human input through explicit, manual feedback (Shah et al., 2018) or implicit signals (e.g. the user interrupting the system or starting over) (Shi and Yu, 2018).”
Domain Adaptive Dialog Generation via Meta Learning (2019, background): “Shi and Yu (2018) introduces an end-to-end dialog system that adapts to user sentiment.”
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good (2019, background): “For instance, Shi and Yu (2018) exploited user sentiment information to make dialogue agent more user-adaptive and effective.”
A survey on empathetic dialogue systems (2020, background): “User’s sentiment in such a case might serve as immediate rewards to the system [50, 45, 49].”
Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog (2019, background): “…use data-driven approaches to build a dialog system from conversational corpora (Zhao and Eskenazi, 2016; Dhingra et al., 2017; Shah et al., 2018; Shi and Yu, 2018), where a common strategy is to build a user simulator, and then to learn dialog policy through making simulated interactions…”