# Few-Shot Generalization Across Dialogue Tasks

arXiv: https://arxiv.org/abs/1811.11707 · HTML: https://mlsanity.com/paper/1811.11707/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 5 of 5)

- [Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System](https://mlsanity.com/paper/2205.04006/) (2022)
- [Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling](https://mlsanity.com/paper/2106.07343/) (2021)
- [LSTM-RASA Based Agri Farm Assistant for Farmers](https://mlsanity.com/paper/2204.09717/) (2022)
- [Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings](https://mlsanity.com/paper/2207.00468/) (2022)
- [Improving Dialogue Management: Quality Datasets vs Models](https://mlsanity.com/paper/2310.01339/) (2023)

## Abstract (arXiv)

Machine-learning based dialogue managers are able to learn complex behaviors in order to complete a task, but it is not straightforward to extend their capabilities to new domains. We investigate different policies' ability to handle uncooperative user behavior, and how well expertise in completing one task (such as restaurant reservations) can be reapplied when learning a new one (e.g. booking a hotel). We introduce the Recurrent Embedding Dialogue Policy (REDP), which embeds system actions and dialogue states in the same vector space. REDP contains a memory component and attention mechanism based on a modified Neural Turing Machine, and significantly outperforms a baseline LSTM classifier on this task. We also show that both our architecture and baseline solve the bAbI dialogue task, achieving 100% test accuracy.