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 Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use

2019 ◽  
Vol 7 ◽  
pp. 375-386
Author(s):  
Janarthanan Rajendran ◽  
Jatin Ganhotra ◽  
Lazaros C. Polymenakos
Keyword(s):  
Customer Service ◽  
User Behavior ◽  
Wait Time ◽  
Test Time ◽  
Dialog Systems ◽  
User Behaviors ◽  
Human Agent ◽  
Task Success ◽  
End To End ◽  
Reduce Wait Time

Neural end-to-end goal-oriented dialog systems showed promise to reduce the workload of human agents for customer service, as well as reduce wait time for users. However, their inability to handle new user behavior at deployment has limited their usage in real world. In this work, we propose an end-to-end trainable method for neural goal-oriented dialog systems that handles new user behaviors at deployment by transferring the dialog to a human agent intelligently. The proposed method has three goals: 1) maximize user’s task success by transferring to human agents, 2) minimize the load on the human agents by transferring to them only when it is essential, and 3) learn online from the human agent’s responses to reduce human agents’ load further. We evaluate our proposed method on a modified-bAbI dialog task, 1 which simulates the scenario of new user behaviors occurring at test time. Experimental results show that our proposed method is effective in achieving the desired goals.

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.

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 MOSS: End-to-End Dialog System Framework with Modular Supervision

2020 ◽  
Vol 34 (05) ◽  
pp. 8327-8335
Author(s):  
Weixin Liang ◽  
Youzhi Tian ◽  
Chengcai Chen ◽  
Zhou Yu
Keyword(s):  
Natural Language ◽  
Customer Service ◽  
State Of The Art ◽  
Training Data ◽  
Language Understanding ◽  
Language Generation ◽  
Dialog System ◽  
Major Bottleneck ◽  
End To End ◽  
Task Oriented

A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning and natural language generation. With only 60% of the training data, MOSS-all (i.e., MOSS with supervision from all four dialog modules) outperforms state-of-the-art models on CamRest676. Moreover, introducing modular supervision has even bigger benefits when the dialog task has a more complex dialog state and action space. With only 40% of the training data, MOSS-all outperforms the state-of-the-art model on a complex laptop network trouble shooting dataset, LaptopNetwork, that we introduced. LaptopNetwork consists of conversations between real customers and customer service agents in Chinese. Moreover, MOSS framework can accommodate dialogs that have supervision from different dialog modules at both framework level and model level. Therefore, MOSS is extremely flexible to update in real-world deployment.

scholarly journals The influence of bank employees on bank customer relationship management

2007 ◽  
Vol 7 (1) ◽  
Author(s):  
C. Rootman ◽  
M. Tait ◽  
J Bosch
Keyword(s):  
South Africa ◽  
South African ◽  
Customer Service ◽  
Customer Relationship Management ◽  
Service Providers ◽  
Relationship Management ◽  
Primary Objective ◽  
Customer Relationship ◽  
Positive Attitudes ◽  
Bank Employees

Purpose: Despite extensive research in services marketing, much is still unknown to specific service providers on the influence of their employees on their services. This paper attempts to address this limitation and investigates the influence of employees on the customer relationship management (CRM) of banks. The primary objective of this paper is to investigate the influence of selected independent variables, namely attitude and knowledgeability, on the CRM of banks.Design/Methodology/Approach: An empirical investigation was conducted with a structured questionnaire with items that related to banks' CRM in terms of attitude and knowledgeability. The sample consisted of 290 banking clients in the Nelson Mandela Metropolitan area and the response rate was 91.03%. Findings: Significant positive relationships exist between both the knowledgeability, and attitude of bank employees and a bank's CRM. These relationships imply that more extensive knowledgeability and more positive attitudes of bank employees lead to improved, maintained relationships between a bank and its clients. Employees play an important role in banks’ client relationships. Implications: Banks should focus on increasing their employees' knowledgeability and improving their attitude to ensure higher levels of CRM. This paper provides strategies for banks and could create greater awareness among South African banks of the advantages of CRM, how their employees influence their CRM, and ways to adapt to these influences. Originality/Value: No study has focused exclusively on CRM within banks in South Africa. Prior research focused on customer service and service quality; both possible results of superior CRM. However, this research differs, as it identifies the variables influencing CRM in banks in South Africa. It is proposed that this paper will be beneficial for South African banks, as the recommendations may be used to ensure higher levels of CRM in banks.

scholarly journals Towards a circumplex typology of customer service experience management practices: a dyadic perspective

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yasin Sahhar ◽  
Raymond Loohuis ◽  
Jörg Henseler
Keyword(s):  
Customer Service ◽  
Management Practices ◽  
Ad Hoc ◽  
Service Providers ◽  
Service Industries ◽  
Customer Journey ◽  
Service Experience ◽  
Content Type ◽  
Knowledge Intensive ◽  
Five Phases

PurposeThe purpose of this study is to identify the practices used by service providers to manage the customer service experience (CSE) across multiple phases of the customer journey in a business-to-business (B2B) setting.Design/methodology/approachThis study comprises an ethnography that investigates in real time, from a dyadic perspective, and the CSE management practices at two service providers operating in knowledge-intensive service industries over a period of eight months. Analytically, the study concentrates on critical events that occurred in phases of the customer journey that in some way alter CSE, thus making it necessary for service providers to act to keep their customers satisfied.FindingsThe study uncovers four types of service provider practices that vary based on the mode of organization (ad hoc or regular) and the mode of engagement (reactive or proactive) and based on whether they restore or bolster CSE, including the recurrence of these practices in the customer journey. These practices are conveniently presented in a circumplex typology of CSE management across five phases in the customer journey.Research limitations/implicationsThis paper advances the research in CSE management throughout the customer journey in the B2B context by showing that CSE management is dynamic, recurrent and multifaceted in the sense that it requires different modes of organization and engagement, notably during interaction with customers, in different phases of the customer journey.Practical implicationsThe circumplex typology acts as a tool for service providers, helping them to redesign their CSE management practices in ongoing service and dialogical processes to keep their customers more engaged and satisfied.Originality/valueThis paper is the first to infuse a dyadic stance into the ongoing discussion of CSE management practices in B2B, in which studies to date have deployed only provider or customer perspectives. In proposing a microlevel view, the study identifies service providers' CSE management practices in multiple customer journey phases, especially when the situation becomes critical.

Sign in / Sign up

Export Citation Format

Share Document