# Dialogue Transformers

arXiv: https://arxiv.org/abs/1910.00486 · HTML: https://mlsanity.com/paper/1910.00486/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2019.

## Built on by (most cited first, 13 of 13)

- [ChatGPT as your Personal Data Scientist](https://mlsanity.com/paper/2305.13657/) (2023)
- [Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System](https://mlsanity.com/paper/2205.04006/) (2022)
- [Dynamic Dialogue Policy for Continual Reinforcement Learning](https://mlsanity.com/paper/2204.05928/) (2022)
- [A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment](https://mlsanity.com/paper/2305.08200/) (2023)
- [Task-Oriented Dialogue with In-Context Learning](https://mlsanity.com/paper/2402.12234/) (2024)
- [Preuve de concept d'un bot vocal dialoguant en wolof](https://mlsanity.com/paper/2404.02009/) (2024)
- [End-to-End Natural Language Understanding Pipeline for Bangla Conversational Agents](https://mlsanity.com/paper/2107.05541/) (2021)
- [End-to-End Evaluation of a Spoken Dialogue System for Learning Basic Mathematics](https://mlsanity.com/paper/2211.03511/) (2022)
- [LSTM-RASA Based Agri Farm Assistant for Farmers](https://mlsanity.com/paper/2204.09717/) (2022)
- [We are all Individuals: The Role of Robot Personality and Human Traits in Trustworthy Interaction](https://mlsanity.com/paper/2307.15568/) (2023)
- [Understanding the Complexity and Its Impact on Testing in ML-Enabled Systems](https://mlsanity.com/paper/2301.03837/) (2023)
- [Improving Dialogue Management: Quality Datasets vs Models](https://mlsanity.com/paper/2310.01339/) (2023)
- [Spoken Dialogue System for Medical Prescription Acquisition on Smartphone: Development, Corpus and Evaluation](https://mlsanity.com/paper/2311.03510/) (2023)

## Abstract (arXiv)

We introduce a dialogue policy based on a transformer architecture, where the self-attention mechanism operates over the sequence of dialogue turns. Recent work has used hierarchical recurrent neural networks to encode multiple utterances in a dialogue context, but we argue that a pure self-attention mechanism is more suitable. By default, an RNN assumes that every item in a sequence is relevant for producing an encoding of the full sequence, but a single conversation can consist of multiple overlapping discourse segments as speakers interleave multiple topics. A transformer picks which turns to include in its encoding of the current dialogue state, and is naturally suited to selectively ignoring or attending to dialogue history. We compare the performance of the Transformer Embedding Dialogue (TED) policy to an LSTM and to the REDP, which was specifically designed to overcome this limitation of RNNs.