• Corpus ID: 234342691

Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey

@article{Ni2021RecentAI,
  title={Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey},
  author={Jinjie Ni and Tom Young and Vlad Pandelea and Fuzhao Xue and V. Ananth Krishna Adiga and E. Cambria},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.04387}
}
Dialogue systems are a popular Natural Language Processing (NLP) task as it is promising in real-life applications. It is also a complicated task since many NLP tasks deserving study are involved. As a result, a multitude of novel works on this task are carried out, and most of them are deep learning-based due to the outstanding performance. In this survey, we mainly focus on the deep learningbased dialogue systems. We comprehensively review state-of-the-art research outcomes in dialogue… 
A Chit-Chats Enhanced Task-Oriented Dialogue Corpora for Fuse-Motive Conversation Systems
TLDR
This work releases a multi-turn dialogues dataset called Chinese ChatEnhanced-Task (CCET) and proposes a line of fuse-motive dialogues formalization approach, along with several evaluation metrics for TOD sessions that are integrated by CC utterances.
Personalizing Dialogue Agents for Russian: Retrieve and Refine
TLDR
A study of Retrieve and Refine models for automatic generation of utterances of a personalized Russian-speaking dialogue agent and a solution based on the BERT encoder model was proposed.
A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective
TLDR
This survey paper overviews major deep learning methods used in Natural Language Processing (NLP) and source code over the last 35 years and presents a software-engineering centered taxonomy for CI placing each of the works into one category describing how it best assists the software development cycle.
On Tracking Dialogue State by Inheriting Slot Values in Mentioned Slot Pools
TLDR
This study designed a model with a mentioned slot pool (MSP) to tackle the update problem of dialogue state tracking, and reached state-of-the-art DST performance on MultiWOZ datasets.
State-of-the-art in Open-domain Conversational AI: A Survey
TLDR
It is shown that hybrid models of conversational AI offer more advantages than any single architecture, and the female gender is more common than the male for conversationalAI.
Unsupervised Knowledge Selection for Dialogue Generation
TLDR
A novel Distilled Distant Supervision Loss (DDSL) is proposed to supervise knowledge selection when the gold knowledge label is unknown and manages to select knowledge more accurately in the unsupervised setting and generates more informative responses, even outperforming many strong supervised baselines.
Robust Dialogue State Tracking with Weak Supervision and Sparse Data
TLDR
A training strategy to build extractive DST models without the need for fine-grained manual span labels, and a new model architecture with a unified encoder that supports value as well as slot independence by leveraging the attention mechanism.
Generative Spoken Dialogue Language Modeling
TLDR
dGSLM is introduced, the first “textless” model able to generate audio samples of naturalistic spoken dialogues and reproduces naturalistic turn taking.
Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
TLDR
The authors' extensive experiments suggest that contextual representations in PLMs do encode metaphorical knowledge, and mostly in their middle layers, and the knowledge is transferable between languages and datasets, especially when the annotation is consistent across training and testing sets.
...
1
2
...

References

SHOWING 1-10 OF 509 REFERENCES
A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
TLDR
This work provides a comprehensive review towards building open domain dialogue systems, an important application of natural language generation, and finds that, predominantly, the approaches for building dialogue systems use seq2seq or language models architecture.
A Survey on Dialogue Systems: Recent Advances and New Frontiers
TLDR
This article generally divides existing dialogue systems into task-oriented and nontask- oriented models, then detail how deep learning techniques help them with representative algorithms and finally discusses some appealing research directions that can bring the dialogue system research into a new frontier.
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
TLDR
This paper introduces Levenshtein belief spans (Lev), that allows efficient dialogue state tracking with a minimal generation length, and greatly improves the inference efficiency of MinTL-based systems.
Training Neural Response Selection for Task-Oriented Dialogue Systems
TLDR
A novel method which pretrains the response selection model on large general-domain conversational corpora and fine-tunes the pretrained model for the target dialogue domain, relying only on the small in-domain dataset to capture the nuances of the given dialogue domain is proposed.
MuTual: A Dataset for Multi-Turn Dialogue Reasoning
TLDR
MuTual is introduced, a novel dataset for Multi-Turn dialogue Reasoning, consisting of 8,860 manually annotated dialogues based on Chinese student English listening comprehension exams, which shows that there is ample room for improving reasoning ability.
Recent Advances on Human-Computer Dialogue
Context-aware Natural Language Generation for Spoken Dialogue Systems
TLDR
A Context-Aware LSTM model for NLG is proposed, which is completely driven by data without manual designed templates or rules, and obtains state-of-the-art performance.
Personalizing a Dialogue System With Transfer Reinforcement Learning
TLDR
This work proposes "PETAL"(PErsonalized Task-oriented diALogue), a transfer-learning framework based on POMDP to learn a personalized dialogue system that can avoid the negative transfer problem by considering differences between source and target users.
End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2
TLDR
This paper presents an end-to-end neural architecture for dialogue systems that addresses both challenges above and achieves the success rate, language understanding, and response appropriateness in the 8th dialogue systems technology challenge (DSTC8).
Multi-Domain Dialogue Acts and Response Co-Generation
TLDR
A neural co-generation model that generates dialogue acts and responses concurrently and achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.
...
1
2
3
4
5
...