# N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking

arXiv: https://arxiv.org/abs/2103.00293 · HTML: https://mlsanity.com/paper/2103.00293/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 27 Feb 2021.

## Builds on (most cited first, 28 of 28)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://mlsanity.com/paper/1805.06201/) (2018)
- [TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://mlsanity.com/paper/2004.06871/) (2020)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [Data Augmentation for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1705.00440/) (2017)
- [Data Noising as Smoothing in Neural Network Language Models](https://mlsanity.com/paper/1703.02573/) (2017)
- [Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding](https://mlsanity.com/paper/1807.01554/) (2018)
- [Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2005.00891/) (2020)
- [Global-Locally Self-Attentive Dialogue State Tracker](https://mlsanity.com/paper/1805.09655/) (2018)
- [Paraphrase Augmented Task-Oriented Dialog Generation](https://mlsanity.com/paper/2004.07462/) (2020)
- [CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers](https://mlsanity.com/paper/2010.12850/) (2020)
- [Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations](https://mlsanity.com/paper/2005.08866/) (2020)
- [Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2008.06239/) (2020)
- [Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling](https://mlsanity.com/paper/2004.11727/) (2020)
- [Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing](https://mlsanity.com/paper/1807.06517/) (2018)
- [Scalable Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/1712.10224/) (2017)
- [Few Shot Dialogue State Tracking using Meta-learning](https://mlsanity.com/paper/2101.06779/) (2021)
- [Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management](https://mlsanity.com/paper/2010.15411/) (2020)
- [Dialog State Tracking with Reinforced Data Augmentation](https://mlsanity.com/paper/1908.07795/) (2019)
- [Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue](https://mlsanity.com/paper/1912.02478/) (2019)
- [Data Augmentation for Copy-Mechanism in Dialogue State Tracking](https://mlsanity.com/paper/2002.09634/) (2020)
- [Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring](https://mlsanity.com/paper/1903.03530/) (2019)
- [Automatic Data Expansion for Customer-care Spoken Language Understanding](https://mlsanity.com/paper/1810.00670/) (2018)

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- ["Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking](https://mlsanity.com/paper/2207.14627/) (2022)
- [Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation](https://mlsanity.com/paper/2306.04724/) (2023)
- [Dual-path Frequency Discriminators for Few-shot Anomaly Detection](https://mlsanity.com/paper/2403.04151/) (2024)
- [Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2405.12468/) (2024)
- [Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions](https://mlsanity.com/paper/2504.18474/) (2025)

## Abstract (arXiv)

Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation strategies, it operates with as few as five examples. Our augmentation strategy yields significant improvements when both adapting a DST model to a new domain, and when adapting a language model to the DST task, on evaluations with TRADE and TOD-BERT models. Further analysis shows that our model performs better on seen values during training, and it is also more robust to unseen values. We conclude that exploiting belief state annotations enhances dialogue augmentation and results in improved models in n-shot training scenarios.