End-to-End Task-Completion Neural Dialogue Systems

By Xiujun Li, Yun-Nung (Vivian) Chen, Lihong Li, Jianfeng Gao, Asli Celikyilmaz. 2017

382 citations recorded by the source corpus.

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance of the entire system is not robust to the accumulated errors. This paper presents a novel end-to-end learning framework for task-completion dialogue systems to tackle such issues.Our neural dialogue system can directly interact with a structured database to assist users in accessing information and accomplishing certain tasks. The reinforcement learning based dialogue manager offers robust capabilities to handle noises caused by other components of the dialogue system. Our experiments in a movie-ticket booking domain show that our end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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 Computer Vision and Pattern Recognition

Citations in the corpus

Incremental Learning from Scratch for Task-Oriented Dialogue Systems (2019, methodology): “Data-driven methods, such as reinforcement learning (Williams et al., 2017; Zhao and Eskenazi, 2016; Li et al., 2017) and supervised learning (Wen et al., 2016; Eric and Manning, 2017; Bordes et al., 2016), have been applied to optimize dialogue systems automatically.”
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, background): “These problems can either be addressed separately (Young et al., 2013), or jointly in an end-to-end fashion (Bordes et al., 2017; Wen et al., 2017; Li et al., 2017).”
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems (2018, methodology): “Our system is trained by a combination of supervised and deep RL methods, as it is shown that RL may effectively improve dialogue success rate by exploring a large dialogue action space (Henderson et al., 2008; Li et al., 2017).”
Iterative policy learning in end-to-end trainable task-oriented neural dialog models (2017, methodology): “User simulators used in most of the recent RL based dialog models [19, 23, 20] are designed with expert knowledge and complex rules.”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “Previous systems achieved this by issuing a symbolic query to the knowledge base to retrieve entries based on their attributes, where semantic parsing on the input is performed to construct a symbolic query representing the beliefs of the agent about the user goal[84; 90; 36].”
Ranking Policy Gradient (2019, methodology): “The MDPs satisfying this condition cover a wide range of tasks such as Dialogue System Li et al. (2017), Go Silver et al. (2017), video games Bellemare et al. (2013) and all MDPs with only one initial state.”
Sentiment Adaptive End-to-End Dialog Systems (2018, background): “Recently, more and more work combines all the modules in an end-to-end training framework (Wen et al., 2016; Li et al., 2017; Dhingra et al., 2016; Williams et al., 2017; Liu and Lane, 2017a).”
Neural Approaches to Conversational AI (2018, positive): “This inspire another line of work that uses reinforcement learning to optimize end-to-end dialogue systems (Zhao and Eskénazi, 2016; Williams and Zweig, 2016; Dhingra et al., 2017; Li et al., 2017d; Braunschweiler and Papangelis, 2018; Strub et al., 2017; Liu and Lane, 2017; Liu et al., 2018a).”
Towards Deep Conversational Recommendations (2018, background): “Other approaches [15, 16, 17, 18] use reinforcement learning to train goal-oriented dialogue systems.”
Hierarchical Pointer Memory Network for Task Oriented Dialogue (2018, background): “Some examples include restaurant reservation (Henderson et al., 2014), movie ticket booking (Li et al., 2017) and bus information system (Raux et al., 2005).”
SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model (2020, background): “End-to-end trainable dialog systems have been studied in (Wen et al., 2016; Zhao and Eskenazi, 2016; Li et al., 2017; Williams et al., 2017; Lei et al., 2018; Gao et al., 2019; Zhang et al., 2019a).”
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management (2020, background): “the past few years, there are many deep reinforcement learning (DRL) algorithms which use neural networks (NN) as function approximators, investigated for dialogue policy [2], [3], [4], [5], [6].”
A Survey on Conversational Recommender Systems (2020, background): “, with respect to fluency, appropriateness, consistency, engagingness, relevance, informativeness, and the overall dialogue quality and generation performance [27, 45, 63, 74, 75, 100, 146].”
Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning (2019, background): “…et al., 2009; Reiter and Dale, 2000; Rieser and Lemon, 2010), especially when adopting deep learning models (Deng and Liu, 2018; Mesnil et al., 2015; Wen et al., 2015, 2017; Su et al., 2017; Papangelis et al., 2018; Liu and Lane, 2018b; Li et al., 2017; Williams et al., 2017; Liu and Lane, 2018a).”
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention (2019, background): “Recently, there have been increasing interests in industrial companies to build task-oriented conversational agents (Wen et al., 2017; Li et al., 2017; Rojas-Barahona et al., 2017) to solve pre-defined tasks such as restaurant or flight bookings, etc (see Figure 1 for an example dialog from MultiWOZ”
Task-oriented Dialogue System for Automatic Diagnosis (2018, methodology): “We follow the same setting as Li et al. (2017) to design our medical DS.”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, background): “The first sees the GAN framework applied to enhance response generation (Li et al., 2017a; Zhu et al., 2018; Wu et al., 2019b; He et al., 2020a; Zhu et al., 2020; Qin et al., 2020).”