A dynamic goal adapted task oriented dialogue agent.
<h4>Purpose</h4>Existing virtual agents (VAs) present in dialogue systems are either information retrieval based or static goal-driven. However, in real-world situations, end-users might not have a known and fixed goal beforehand for the task, i.e., they may upgrade/downgrade/update thei...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2021-01-01
|
Series: | PLoS ONE |
Online Access: | https://doi.org/10.1371/journal.pone.0249030 |
id |
doaj-7df078ed18384e6fb912510303f4a948 |
---|---|
record_format |
Article |
spelling |
doaj-7df078ed18384e6fb912510303f4a9482021-04-11T04:30:27ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01164e024903010.1371/journal.pone.0249030A dynamic goal adapted task oriented dialogue agent.Abhisek TiwariTulika SahaSriparna SahaShubhashis SenguptaAnutosh MaitraRoshni RamnaniPushpak Bhattacharyya<h4>Purpose</h4>Existing virtual agents (VAs) present in dialogue systems are either information retrieval based or static goal-driven. However, in real-world situations, end-users might not have a known and fixed goal beforehand for the task, i.e., they may upgrade/downgrade/update their goal components in real-time to maximize their utility values. Existing VAs are unable to handle such dynamic goal-oriented situations.<h4>Methodology</h4>Due to the absence of any related dialogue dataset where such choice deviations are present, we have created a conversational dataset called Deviation adapted Virtual Agent(DevVA), with the manual annotation of its corresponding intents, slots, and sentiment labels. A Dynamic Goal Driven Dialogue Agent (DGDVA) has been developed by incorporating a Dynamic Goal Driven Module (GDM) on top of a deep reinforcement learning based dialogue manager. In the course of a conversation, the user sentiment provides grounded feedback about agent behavior, including goal serving action. User sentiment appears to be an appropriate indicator for goal discrepancy that guides the agent to complete the user's desired task with gratification. The negative sentiment expressed by the user about an aspect of the provided choice is treated as a discrepancy that is being resolved by the GDM depending upon the observed discrepancy and current dialogue state. The goal update capability and the VA's interactiveness trait enable end-users to accomplish their desired task satisfactorily.<h4>Findings</h4>The obtained experimental results illustrate that DGDVA can handle dynamic goals with maximum user satisfaction and a significantly higher success rate. The interaction drives the user to decide its final goal through the latent specification of possible choices and information retrieved and provided by the dialogue agent. Through the experimental results (qualitative and quantitative), we firmly conclude that the proposed sentiment-aware VA adapts users' dynamic behavior for its goal setting with substantial efficacy in terms of primary objective i.e., task success rate (0.88).<h4>Practical implications</h4>In real world, it can be argued that many people do not have a predefined and fixed goal for tasks such as online shopping, movie booking & restaurant booking, etc. They tend to explore the available options first which are aligned with their minimum requirements and then decide one amongst them. The DGDVA provides maximum user satisfaction as it enables them to accomplish a dynamic goal that leads to additional utilities along with the essential ones.<h4>Originality</h4>To the best of our knowledge, this is the first effort towards the development of A Dynamic Goal Adapted Task-Oriented Dialogue Agent that can serve user goals dynamically until the user is satisfied.https://doi.org/10.1371/journal.pone.0249030 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Abhisek Tiwari Tulika Saha Sriparna Saha Shubhashis Sengupta Anutosh Maitra Roshni Ramnani Pushpak Bhattacharyya |
spellingShingle |
Abhisek Tiwari Tulika Saha Sriparna Saha Shubhashis Sengupta Anutosh Maitra Roshni Ramnani Pushpak Bhattacharyya A dynamic goal adapted task oriented dialogue agent. PLoS ONE |
author_facet |
Abhisek Tiwari Tulika Saha Sriparna Saha Shubhashis Sengupta Anutosh Maitra Roshni Ramnani Pushpak Bhattacharyya |
author_sort |
Abhisek Tiwari |
title |
A dynamic goal adapted task oriented dialogue agent. |
title_short |
A dynamic goal adapted task oriented dialogue agent. |
title_full |
A dynamic goal adapted task oriented dialogue agent. |
title_fullStr |
A dynamic goal adapted task oriented dialogue agent. |
title_full_unstemmed |
A dynamic goal adapted task oriented dialogue agent. |
title_sort |
dynamic goal adapted task oriented dialogue agent. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2021-01-01 |
description |
<h4>Purpose</h4>Existing virtual agents (VAs) present in dialogue systems are either information retrieval based or static goal-driven. However, in real-world situations, end-users might not have a known and fixed goal beforehand for the task, i.e., they may upgrade/downgrade/update their goal components in real-time to maximize their utility values. Existing VAs are unable to handle such dynamic goal-oriented situations.<h4>Methodology</h4>Due to the absence of any related dialogue dataset where such choice deviations are present, we have created a conversational dataset called Deviation adapted Virtual Agent(DevVA), with the manual annotation of its corresponding intents, slots, and sentiment labels. A Dynamic Goal Driven Dialogue Agent (DGDVA) has been developed by incorporating a Dynamic Goal Driven Module (GDM) on top of a deep reinforcement learning based dialogue manager. In the course of a conversation, the user sentiment provides grounded feedback about agent behavior, including goal serving action. User sentiment appears to be an appropriate indicator for goal discrepancy that guides the agent to complete the user's desired task with gratification. The negative sentiment expressed by the user about an aspect of the provided choice is treated as a discrepancy that is being resolved by the GDM depending upon the observed discrepancy and current dialogue state. The goal update capability and the VA's interactiveness trait enable end-users to accomplish their desired task satisfactorily.<h4>Findings</h4>The obtained experimental results illustrate that DGDVA can handle dynamic goals with maximum user satisfaction and a significantly higher success rate. The interaction drives the user to decide its final goal through the latent specification of possible choices and information retrieved and provided by the dialogue agent. Through the experimental results (qualitative and quantitative), we firmly conclude that the proposed sentiment-aware VA adapts users' dynamic behavior for its goal setting with substantial efficacy in terms of primary objective i.e., task success rate (0.88).<h4>Practical implications</h4>In real world, it can be argued that many people do not have a predefined and fixed goal for tasks such as online shopping, movie booking & restaurant booking, etc. They tend to explore the available options first which are aligned with their minimum requirements and then decide one amongst them. The DGDVA provides maximum user satisfaction as it enables them to accomplish a dynamic goal that leads to additional utilities along with the essential ones.<h4>Originality</h4>To the best of our knowledge, this is the first effort towards the development of A Dynamic Goal Adapted Task-Oriented Dialogue Agent that can serve user goals dynamically until the user is satisfied. |
url |
https://doi.org/10.1371/journal.pone.0249030 |
work_keys_str_mv |
AT abhisektiwari adynamicgoaladaptedtaskorienteddialogueagent AT tulikasaha adynamicgoaladaptedtaskorienteddialogueagent AT sriparnasaha adynamicgoaladaptedtaskorienteddialogueagent AT shubhashissengupta adynamicgoaladaptedtaskorienteddialogueagent AT anutoshmaitra adynamicgoaladaptedtaskorienteddialogueagent AT roshniramnani adynamicgoaladaptedtaskorienteddialogueagent AT pushpakbhattacharyya adynamicgoaladaptedtaskorienteddialogueagent AT abhisektiwari dynamicgoaladaptedtaskorienteddialogueagent AT tulikasaha dynamicgoaladaptedtaskorienteddialogueagent AT sriparnasaha dynamicgoaladaptedtaskorienteddialogueagent AT shubhashissengupta dynamicgoaladaptedtaskorienteddialogueagent AT anutoshmaitra dynamicgoaladaptedtaskorienteddialogueagent AT roshniramnani dynamicgoaladaptedtaskorienteddialogueagent AT pushpakbhattacharyya dynamicgoaladaptedtaskorienteddialogueagent |
_version_ |
1714684365932331008 |