Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
By Giovanni Campagna, Agata Foryciarz, Mehrad Moradshahi, Monica S. Lam. 2020
100 citations recorded by the source corpus.
Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique for dialogue state tracking where the in-domain training data are all synthesized from an abstract dialogue model and the ontology of the domain. We show that data augmentation through synthesized data can improve the accuracy of zero-shot learning for both the TRADE model and the BERT-based SUMBT model on the MultiWOZ 2.1 dataset. We show training with only synthesized in-domain data on the SUMBT model can reach about 2/3 of the accuracy obtained with the full training dataset. We improve the zero-shot learning state of the art on average across domains by 21%.
Subfields: Artificial Intelligence, Dialogue & Conversational AI
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
- Mohit Bansal
- Jianfeng Gao
- Percy Liang
- Luke S. Zettlemoyer
- Caiming Xiong
- Richard Socher
- Noah A. Smith
- Graham Neubig
In Dialogue & Conversational AI
Citations in the corpus
- Reasoning Like Program Executors (2022, methodology): “, 2021), generated by a model-based generator (Asai and Hajishirzi, 2020), or synthesized via human-designed templates (Geva et al., 2020; Yoran et al., 2022; Campagna et al., 2020; Wang et al., 2022).”
- A Survey of Data Augmentation Approaches for NLP (2021, background): “Studies have shown that DA becomes less beneficial when applied to out-of-domain data, likely because the distribution of augmented data can substantially differ from the original data (Zhang et al., 2019a; Herzig et al., 2020; Campagna et al., 2020; Zhong et al., 2020).”
- Constrained Language Models Yield Few-Shot Semantic Parsers (2021, background): “…on quickly bootstrapping a semantic parser has focused on creating synthetic training examples from a grammar developed by hand (Campagna et al., 2019; Weir et al., 2020; Marzoev et al., 2020; Campagna et al., 2020) or derived automatically from existing data (Jia and Liang, 2016; Yu et al., 2020).”
- Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking (2021, background): “On the other hand, Campagna et al. (2020) proposed an abstract dialogue model that leverages the ontology and in-domain templates to generate a large amount of synthesized data for domain adaptation.”
- Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021, background): “1 dialogs (Eric et al., 2020) and the off-the-shelf synthesized dialogs (Campagna et al., 2020), which contains 337,346 dialog data in total.”
- AutoQA: From Databases to Q&A Semantic Parsers with Only Synthetic Training Data (2020, unknown): “Training with synthetic data has also been explored to complement existed dataset (Weir et al., 2020) and in the few-shot setting (Campagna et al., 2020; Moradshahi et al., 2020).”
- GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing (2020, background): “More and more work (Zhang et al., 2019b; Herzig et al., 2020b; Campagna et al., 2020; Zhong et al., 2020) shows utilizing augmented data doesn’t always result in a significant performance gain in cross-domain semantic parsing end tasks.”
- Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “(2020c) applied model-agnostic meta-learning (MAML) to first learn on several source domains and then adapt on the target domain, while Campagna et al. (2020) improved the zero-shot transfer learning by synthesizing in-domain data using an abstract conversation model and the domain ontology. Ouyang ”