Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

Dhingra, Bhuwan; Li, Lihong; Li, Xiujun; Gao, Jianfeng; Chen, Yun-Nung; Ahmed, Faisal; Deng, Li

doi:10.48550/arxiv.1609.00777

Cited by 37 publications

(42 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attempts to open-domain dialog generation include generating more coherent [1,41,42], diverse [5,77], personalized [40,55] utterances. With the emergence of task-oriented datasets [7,17,66,74], more practice has been devoted to task-oriented dialog generation, which usually involves a pipeline of intent classification [67], dialog state tracking [25][26][27], dialog policy making [10,45] and dialog generation [15]. Dialog state tracking, due to its importance in bridging the user's intent and certain dialog states, has gained numerous attention over recent years [4,16,21,28,36,44,57,75].…”

Section: Textual Dialog Generationmentioning

confidence: 99%

Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation

Wang¹,

Meng²,

Sun³

et al. 2021

Preprint

View full text Add to dashboard Cite

Multi-modal dialog modeling is of growing interest. In this work, we propose frameworks to resolve a specific case of multi-modal dialog generation that better mimics multi-modal dialog generation in the real world, where each dialog turn is associated with the visual context in which it takes place. Specifically, we propose to model the mutual dependency between text-visual features, where the model not only needs to learn the probability of generating the next dialog utterance given preceding dialog utterances and visual contexts, but also the probability of predicting the visual features in which a dialog utterance takes place, leading the generated dialog utterance specific to the visual context. We observe significant performance boosts over vanilla models when the mutual dependency between text and visual features is modeled. 1

show abstract

Section: Textual Dialog Generationmentioning

confidence: 99%

Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation

Wang¹,

Meng²,

Sun³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Xxx represent a reinforcement learning-based spoken dialog system in which the annotation costs are reduced. In 2017, many end-to-end proposals for dialog system emerge rather than hand-craft features based on reinforcement learning and natural language processing methods [43,44,45,46,47]. End-to-end method can be built based on data purely, but the interpretability of the model need to be concerned.…”

Section: Ai-based Implementationmentioning

confidence: 99%

Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field

Huang¹,

Chen²,

Tang³

2021

Preprint

View full text Add to dashboard Cite

We introduce a framework for AI-based medical consultation system with knowledge graph embedding and reinforcement learning components and its implement. Our implement of this framework leverages knowledge organized as a graph to have diagnosis according to evidence collected from patients recurrently and dynamically. According to experiment we designed for evaluating its performance, it archives a good result. More importantly, for getting better performance, researchers can implement it on this framework based on their innovative ideas, well designed experiments and even clinical trials.

show abstract

“…The development of natural language (NL) understanding and dialogue systems, both spoken and textbased, has over 30 years of history and can be divided into three generations according to the disparate styles of system design: (1) use of expert systems based on symbolic-rules and templates (Allen et al, 1996;Rudnicky and Xu, 1999), (2) use of (shallow) statistical learning (Wang et al, 2005;Tur and Deng, 2011;Wang et al, 2011), and (3) use of deep learning (Tur et al, 2018;Dhingra et al, 2016). The earlier two generations of dialogue systems were usually designed with a number of separate modules: textual (or spoken) natural language understanding (NLU), dialogue manager, natural language generation (NLG), and (optionally) spoken language generation.…”

Section: Introductionmentioning

confidence: 99%

MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System

Rhys¹,

Valmianski²,

Deng³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present MEDCOD, a Medically-Accurate, Emotive, Diverse, and Controllable Dialog system with a unique approach to the natural language generator module. MEDCOD has been developed and evaluated specifically for the history taking task. It integrates the advantage of a traditional modular approach to incorporate (medical) domain knowledge with modern deep learning techniques to generate flexible, human-like natural language expressions. Two key aspects of MEDCOD's natural language output are described in detail. First, the generated sentences are emotive and empathetic, similar to how a doctor would communicate to the patient. Second, the generated sentence structures and phrasings are varied and diverse while maintaining medical consistency with the desired medical concept (provided by the dialogue manager module of MEDCOD). Experimental results demonstrate the effectiveness of our approach in creating a human-like medical dialogue system. Relevant code is available at https://github.com/ curai/curai-research/tree/main/MEDCOD

show abstract

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

Cited by 37 publications

References 22 publications

Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation

Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation

Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field

MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System

Contact Info

Product

Resources

About