A Review of Dialogue Systems: From Trained Monkeys to Stochastic Parrots
Not on the map. Why?
Abstract (arXiv)
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. Dialogue systems are increasingly being designed to move beyond just imitating conversation and also improve from such interactions over time. In this survey, we present a broad overview of methods developed to build dialogue systems over the years. Different use cases for dialogue systems ranging from task-based systems to open domain chatbots motivate and necessitate specific systems. Starting from simple rule-based systems, research has progressed towards increasingly complex architectures trained on a massive corpus of datasets, like deep learning systems. Motivated with the intuition of resembling human dialogues, progress has been made towards incorporating emotions into the natural language generator, using reinforcement learning. While we see a trend of highly marginal improvement on some metrics, we find that limited justification exists for the metrics, and evaluation practices are not uniform. To conclude, we flag these concerns and highlight possible research directions.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 73 references that are in the map. First posted on arXiv 2 Nov 2021.
Builds on
28 of 73 references.
References · 28
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
- 2020Towards a Human-like Open-Domain Chatbotcited by 467
- 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
- 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
- 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
- 2019BERT for Joint Intent Classification and Slot Fillingcited by 195
- 2019The Evolved Transformercited by 180
- 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
- 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 142
- 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
16 more
- 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
- 2015Neural Responding Machine for Short-Text Conversationcited by 124
- 2016Learning End-to-End Goal-Oriented Dialogcited by 104
- 2017Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responsescited by 98
- 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
- 2018Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systemscited by 70
- 2014Addressing the Rare Word Problem in Neural Machine Translationcited by 50
- 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 44
- 2019Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialogcited by 37
- 2019Multi-lingual Intent Detection and Slot Filling in a Joint BERT-based Modelcited by 24
- 2017End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradientcited by 23
- 2018Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learningcited by 21
- 2020Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluationcited by 19
- 2015Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Rerankingcited by 17
- 2018Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learningcited by 12
- 2016End-to-end LSTM-based dialog control optimized with supervised and reinforcement learningcited by 8
Built on by
Citing papers per year: 2023: 1.
1 paper.