# A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOS

arXiv: https://arxiv.org/abs/2212.03817 · HTML: https://mlsanity.com/paper/2212.03817/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://mlsanity.com/paper/1606.03777/) (2016)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1905.06874/) (2019)
- [Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1812.09471/) (2018)
- [End-to-End Task-Completion Neural Dialogue Systems](https://mlsanity.com/paper/1703.01008/) (2017)
- [Ask the Right Questions: Active Question Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1705.07830/) (2017)
- [Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention](https://mlsanity.com/paper/1905.12866/) (2019)
- [Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge](https://mlsanity.com/paper/2104.06828/) (2021)
- [Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base](https://mlsanity.com/paper/1910.05069/) (2019)
- [MIMICS: A Large-Scale Data Collection for Search Clarification](https://mlsanity.com/paper/2006.10174/) (2020)
- [Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations](https://mlsanity.com/paper/2010.02495/) (2020)
- [Feedback-Based Self-Learning in Large-Scale Conversational AI Agents](https://mlsanity.com/paper/1911.02557/) (2019)
- [Multi-domain Conversation Quality Evaluation via User Satisfaction Estimation](https://mlsanity.com/paper/1911.08567/) (2019)
- [User Engagement Prediction for Clarification in Search](https://mlsanity.com/paper/2102.04163/) (2021)
- [Non-Autoregressive Neural Text-to-Speech](https://mlsanity.com/paper/1905.08459/) (2019)
- [Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks](https://mlsanity.com/paper/1910.01302/) (2019)
- [Design Considerations For Hypothesis Rejection Modules In Spoken Language Understanding Systems](https://mlsanity.com/paper/2211.09711/) (2022)

## Built on by (most cited first, 2 of 2)

- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction](https://mlsanity.com/paper/2505.18731/) (2025)

## Abstract (arXiv)

Recently, spoken dialogue systems have been widely deployed in a variety of applications, serving a huge number of end-users. A common issue is that the errors resulting from noisy utterances, semantic misunderstandings, or lack of knowledge make it hard for a real system to respond properly, possibly leading to an unsatisfactory user experience. To avoid such a case, we consider a proactive interaction mechanism where the system predicts the user satisfaction with the candidate response before giving it to the user. If the user is not likely to be satisfied according to the prediction, the system will ask the user a suitable question to determine the real intent of the user instead of providing the response directly. With such an interaction with the user, the system can give a better response to the user. Previous models that predict the user satisfaction are not applicable to DuerOS which is a large-scale commercial dialogue system. They are based on hand-crafted features and thus can hardly learn the complex patterns lying behind millions of conversations and temporal dependency in multiple turns of the conversation. Moreover, they are trained and evaluated on the benchmark datasets with adequate labels, which are expensive to obtain in a commercial dialogue system. To face these challenges, we propose a pipeline to predict the user satisfaction to help DuerOS decide whether to ask for clarification in each turn. Specifically, we propose to first generate a large number of weak labels and then train a transformer-based model to predict the user satisfaction with these weak labels. Empirically, we deploy and evaluate our model on DuerOS, and observe a 19% relative improvement on the accuracy of user satisfaction prediction and 2.3% relative improvement on user experience.