# Chat, Shift and Perform: Bridging the Gap between Task-oriented and Non-task-oriented Dialog Systems

arXiv: https://arxiv.org/abs/2206.11813 · HTML: https://mlsanity.com/paper/2206.11813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 5 Jun 2022.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Leveraging Pre-trained Checkpoints for Sequence Generation Tasks](https://mlsanity.com/paper/1907.12461/) (2019)
- [Towards Knowledge-Based Recommender Dialog System](https://mlsanity.com/paper/1908.05391/) (2019)
- [Learning End-to-End Goal-Oriented Dialog](https://mlsanity.com/paper/1605.07683/) (2016)
- [CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation](https://mlsanity.com/paper/2010.10333/) (2020)
- [Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability](https://mlsanity.com/paper/1706.08476/) (2017)
- [Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems](https://mlsanity.com/paper/1705.00746/) (2017)

## Abstract (arXiv)

We propose CASPER (ChAt, Shift and PERform), a novel dialog system consisting of three types of dialog models: chatter, shifter, and performer. Shifter, which is designed for topic switching, enables a seamless flow of dialog from open-domain chat- to task-oriented dialog. In a user study, CASPER gave a better impression in terms of naturalness of response, lack of forced topic switching, and satisfaction compared with a baseline dialog system trained in an end-to-end manner. In an ablation study, we found that naturalness of response, dialog satisfaction, and task-elicitation rate improved compared with when shifter was removed from CASPER, indicating that topic shift with shifter supports the introduction of natural task-oriented dialog.