# A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example

arXiv: https://arxiv.org/abs/2205.06436 · HTML: https://mlsanity.com/paper/2205.06436/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 13 May 2022.

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

- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [Text Classification Algorithms: A Survey](https://mlsanity.com/paper/1904.08067/) (2019)
- [Adding Chit-Chat to Enhance Task-Oriented Dialogues](https://mlsanity.com/paper/2010.12757/) (2020)
- [Few-shot Intent Classification and Slot Filling with Retrieved Examples](https://mlsanity.com/paper/2104.05763/) (2021)
- [AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience](https://mlsanity.com/paper/1801.05032/) (2018)
- [Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems](https://mlsanity.com/paper/2104.09088/) (2021)

## Built on by (most cited first, 1 of 1)

- [Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation](https://mlsanity.com/paper/2304.00884/) (2023)

## Abstract (arXiv)

Though widely used in industry, traditional task-oriented dialogue systems suffer from three bottlenecks: (i) difficult ontology construction (e.g., intents and slots); (ii) poor controllability and interpretability; (iii) annotation-hungry. In this paper, we propose to represent utterance with a simpler concept named Dialogue Action, upon which we construct a tree-structured TaskFlow and further build task-oriented chatbot with TaskFlow as core component. A framework is presented to automatically construct TaskFlow from large-scale dialogues and deploy online. Our experiments on real-world after-sale customer services show TaskFlow can satisfy the major needs, as well as reduce the developer burden effectively.