scholarly journals Towards Logically Progressive Dialog for Future TODS to Serve in Complex Domains

2019 ◽  
pp. 184-192
Author(s):  
K. Mugoye ◽  
H. O. Okoyo ◽  
S. O. Mc Oyowo
Keyword(s):  
Information Retrieval ◽  
Reinforcement Learning ◽  
Future Studies ◽  
Dialog Systems ◽  
Dialog System ◽  
Task Oriented

Complex domains demand task-oriented dialog system (TODS) to be able to reason and engage with humans in dialog and in information retrieval. This may require contemporary dialog systems to have improved conversation handling capabilities. One stating point is supporting conversations which logically advances, such that they could be able to handle sub dialogs meant to elicit more information, within a topic. This paper presents some findings on the research that has been carried out by the authors with regard to highlighting this problem and suggesting a possible solution. A solution which intended to minimize heavy reliance on handcrafts which have varying challenges. The study discusses an experiment for evaluating a novel architecture envisioned to improve this conversational requirement. The experiment results clearly depict the extent to which we have achieved this desired progression, the underlying effects to users and the potential implications to application. The study recommends combining Agency and Reinforcement learning to deliver the solution and could guide future studies towards achieving even more natural conversations.

scholarly journals Learning Conversational Systems that Interleave Task and Non-Task Content

2017 ◽  
Author(s):  
Zhou Yu ◽  
Alexander Rudnicky ◽  
Alan Black
Keyword(s):  
Customer Service ◽  
Service Providers ◽  
Dialog Systems ◽  
Dialog System ◽  
Task Success ◽  
Personal Assistants ◽  
Task Oriented ◽  
Smooth Transitions ◽  
Oriented System ◽  
Task Content

Task-oriented dialog systems have been applied in various tasks, such as automated personal assistants, customer service providers and tutors. These systems work well when users have clear and explicit intentions that are well-aligned to the systems' capabilities. However, they fail if users intentions are not explicit.To address this shortcoming, we propose a framework to interleave non-task content (i.e.everyday social conversation) into task conversations. When the task content fails, the system can still keep the user engaged with the non-task content. We trained a policy using reinforcement learning algorithms to promote long-turn conversation coherence and consistency, so that the system can have smooth transitions between task and non-task content.To test the effectiveness of the proposed framework, we developed a movie promotion dialog system. Experiments with human users indicate that a system that interleaves social and task content achieves a better task success rate and is also rated as more engaging compared to a pure task-oriented system.

scholarly journals A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing

2018 ◽  
Vol 2018 ◽  
pp. 1-11
Author(s):  
A-Yeong Kim ◽  
Hyun-Je Song ◽  
Seong-Bae Park
Keyword(s):  
Attention Mechanism ◽  
Data Set ◽  
Dialog Systems ◽  
Dialog System ◽  
Fast Training ◽  
Proposed Model ◽  
Spoken Dialog System ◽  
State Tracking ◽  
Dialog State Tracking ◽  
Task Oriented

Dialog state tracking in a spoken dialog system is the task that tracks the flow of a dialog and identifies accurately what a user wants from the utterance. Since the success of a dialog is influenced by the ability of the system to catch the requirements of the user, accurate state tracking is important for spoken dialog systems. This paper proposes a two-step neural dialog state tracker which is composed of an informativeness classifier and a neural tracker. The informativeness classifier which is implemented by a CNN first filters out noninformative utterances in a dialog. Then, the neural tracker estimates dialog states from the remaining informative utterances. The tracker adopts the attention mechanism and the hierarchical softmax for its performance and fast training. To prove the effectiveness of the proposed model, we do experiments on dialog state tracking in the human-human task-oriented dialogs with the standard DSTC4 data set. Our experimental results prove the effectiveness of the proposed model by showing that the proposed model outperforms the neural trackers without the informativeness classifier, the attention mechanism, or the hierarchical softmax.

Application-Independent Knowledge-Processing in a Task-Oriented Speech-Dialog-System (Applikationsunabhängige Wissensverarbeitung in aufgabenorientierten Sprach-Dialogsystemen)

2004 ◽  
Vol 46 (6) ◽  
Author(s):  
Jürgen te Vrugt ◽  
Thomas Portele
Keyword(s):  
Building Blocks ◽  
Spoken Language ◽  
Knowledge Sources ◽  
Knowledge Processing ◽  
Control Applications ◽  
Dialog Systems ◽  
Dialog System ◽  
Run Time ◽  
Task Oriented

SummarySpoken language dialog systems allow users to control applications by voice. These systems tightly integrate the applications to control them, even though knowledge sources of the building blocks are often configurable. Some dialog systems controlling multiple applications loosen the coupling.This article introduces a dialog system accessing multiple applications with a dynamic setup that can be changed at run-time, separating the applications from the system. This is achieved by application-independent knowledge processing inside the dialog system based on modular ontological descriptions. A clear interface between dialog system and applications is provided, generic dialog functionality is realized on top of the application independent knowledge processing. Examples illustrate interactions with the system.

scholarly journals Task-Oriented Dialog Systems That Consider Multiple Appropriate Responses under the Same Context

2020 ◽  
Vol 34 (05) ◽  
pp. 9604-9611
Author(s):  
Yichi Zhang ◽  
Zhijian Ou ◽  
Zhou Yu
Keyword(s):  
Data Augmentation ◽  
State Of The Art ◽  
Task Completion ◽  
Dialog Systems ◽  
State Action ◽  
Response Diversity ◽  
Dialog System ◽  
Additional State ◽  
The One ◽  
Task Oriented

Conversations have an intrinsic one-to-many property, which means that multiple responses can be appropriate for the same dialog context. In task-oriented dialogs, this property leads to different valid dialog policies towards task completion. However, none of the existing task-oriented dialog generation approaches takes this property into account. We propose a Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses. Specifically, we first use dialog states to summarize the dialog history, and then discover all possible mappings from every dialog state to its different valid system actions. During dialog system training, we enable the current dialog state to map to all valid system actions discovered in the previous process to create additional state-action pairs. By incorporating these additional pairs, the dialog policy learns a balanced action distribution, which further guides the dialog model to generate diverse responses. Experimental results show that the proposed framework consistently improves dialog policy diversity, and results in improved response diversity and appropriateness. Our model obtains state-of-the-art results on MultiWOZ.

End-to-End Task-Oriented Dialog System Through Template Slot Value Generation

2020 ◽  
Author(s):  
Teakgyu Hong ◽  
Oh-Woog Kwon ◽  
Young-Kil Kim
Keyword(s):  
Dialog System ◽  
End To End ◽  
Task Oriented

Assessing user simulation for dialog systems using human judges and automatic evaluation measures

2011 ◽  
Vol 17 (4) ◽  
pp. 511-540 ◽  
Author(s):  
HUA AI ◽  
DIANE LITMAN
Keyword(s):  
Gold Standard ◽  
System Development ◽  
Automatic Evaluation ◽  
Dialog Systems ◽  
Evaluation Measures ◽  
Assessment Study ◽  
User Simulation ◽  
Dialog System ◽  
Ranking Model

AbstractWhile different user simulations are built to assist dialog system development, there is an increasing need to quickly assess the quality of the user simulations reliably. Previous studies have proposed several automatic evaluation measures for this purpose. However, the validity of these evaluation measures has not been fully proven. We present an assessment study in which human judgments are collected on user simulation qualities as the gold standard to validate automatic evaluation measures. We show that a ranking model can be built using the automatic measures to predict the rankings of the simulations in the same order as the human judgments. We further show that the ranking model can be improved by using a simple feature that utilizes time-series analysis.

Adversarial approach to domain adaptation for reinforcement learning on dialog systems

2019 ◽  
Vol 128 ◽  
pp. 467-473 ◽  
Author(s):  
Sangjun Koo ◽  
Hwanjo Yu ◽  
Gary Geunbae Lee
Keyword(s):  
Reinforcement Learning ◽  
Domain Adaptation ◽  
Dialog Systems
Sign in / Sign up

Export Citation Format

Share Document