A Survey on Dialogue Systems: Recent Advances and New Frontiers

By Hongshen Chen, Xiaorui Liu, Dawei Yin, Jiliang Tang. 2017

774 citations recorded by the source corpus.

Dialogue systems have attracted more and more attention. Recent advances on dialogue systems are overwhelmingly contributed by deep learning techniques, which have been employed to enhance a wide range of big data applications such as computer vision, natural language processing, and recommender systems. For dialogue systems, deep learning can leverage a massive amount of data to learn meaningful feature representations and response generation strategies, while requiring a minimum amount of hand-crafting. In this article, we give an overview to these recent advances on dialogue systems from various perspectives and discuss some possible research directions. In particular, we generally divide existing dialogue systems into task-oriented and nontask- oriented models, then detail how deep learning techniques help them with representative algorithms and finally discuss some appealing research directions that can bring the dialogue system research into a new frontier

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Does Gender Matter? Towards Fairness in Dialogue Systems (2019, background): “Typical chit-chat dialogue models can be categorized into two classes (Chen et al., 2017): generative models and retrieval models.”
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage (2022, background): “Open-domain dialogue models While opendomain dialogue has a rich history (Chen et al., 2017; Gao et al., 2019; Ni et al., 2021) the area has made significant recent progress by pre-training ever-larger neural models.”
Keep CALM and Explore: Language Models for Action Generation in Text-based Games (2020, background): “More broadly, the concept of generating candidates and re-ranking has been studied in other interactive lanugage tasks such as dialogue (Zhao and Eskenazi, 2016; Williams et al., 2017; Song et al., 2016; Chen et al., 2017) and communication games (Lazaridou et al., 2020).”
Neural Approaches to Conversational AI (2018, background): “(Chen et al., 2017a) reviewed popular deep neural network models for dialogue, focusing only on supervised learning approaches.”
A Survey of Reinforcement Learning Informed by Natural Language (2019, methodology): “The two have been a historical focus in NLP research and are extensively reviewed by [Chen et al. , 2017b] and [Bouziane et al. , 2015] respectively.”
Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models (2020, background): “Recently, because of the advent of a series of deep learning models and the appearance of large-scale real dialogue corpora, end-to-end neural generative dialogue models emerge (Chen et al., 2017).”
Domain Adaptive Dialog Generation via Meta Learning (2019, methodology): “The traditional method to build a dialog system is to train modules separately (Chen et al., 2017) such as: natural language understanding (NLU) (Deng et al.”
FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning (2021, neutral): “Furthermore, the dialogue history from the same speaker is also critical for modeling the logical consistency (Chen et al., 2017).”
Dense Text Retrieval Based on Pretrained Language Models: A Survey (2022, background): “As one of the most essential techniques to overcome information overload, text retrieval systems have been widely employed to support many downstream applications, including question answering [1], [2], dialog system [3], [4], entity linking [5], [6] and Web search [7].”
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models (2023, neutral): “…language models were built on the backbones of n-grams (Bickel et al., 2005; Pauls and Klein, 2011) and recurrent neural networks (Mikolov et al., 2010), and have been applied to various NLG tasks such as summarization (Nallapati et al., 2017) and dialogue generation (Chen et al., 2017).”
Treating Dialogue Quality Evaluation as an Anomaly Detection Problem (2020, background): “Recently, machine-learning powered dialogue systems have been gathering much attention from industry and academia alike (Chen et al., 2017).”
Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation (2018, methodology): “In previous works, a task manager, composed of a database and a query manager [6, 41], is used by the DM to generate observations in retrieval tasks.”
ConveRT: Efficient and Accurate Conversational Representations from Transformers (2019, background): “, 2018), language learning (Raux et al., 2003; Chen et al., 2017), entertainment (Fraser et al.”
Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures (2018, background): “Their proposed architectures follow traditional pipeline designs, where the belief tracking component is the key component (Chen et al., 2017).”
An Application-Independent Approach to Building Task-Oriented Chatbots with Interactive Continual Learning (2020, background): “Note that, CML is not a full-ﬂedged task-oriented dialogue system as it does not have a dialogue manager responsible for dialogue state tracking and dialogue policy or perform multi-turn dialogues [7, 45].”
Transfer Learning in Deep Reinforcement Learning: A Survey (2020, background): “Applications of RL on NLP range widely, from Question Answering (QA) [145], Dialogue”
Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models (2023, background): “Language models can power the development of chatbots, which serve as conversational agents that engage with users in a manner reminiscent of human interaction [14].”
A Repository of Conversational Datasets (2019, background): “, 2018), language learning (Raux et al., 2003; Chen et al., 2017), and healthcare (Laranjo et al.”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, background): “For example, while task-oriented dialogue systems aim to fulﬁll a certain task in human-machine dialogue, the concentration of eﬀort is mainly on handling information in the textural language-based dialogue, e.g., natural language understanding (NLU), dialogue state tracking (DST), dialogue policy l”