Chat Failures and Troubles: Reasons and Solutions

Manal Helal; Patrick Holthaus; Gabriella Lakatos; Farshid Amirabdollahian

doi:10.48550/arXiv.2309.03708

Chat Failures and Troubles: Reasons and Solutions

Manal Helal, Patrick Holthaus, Gabriella Lakatos, Farshid Amirabdollahian

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper examines some common problems in Human-Robot Interaction (HRI) causing failures and troubles in Chat. A given use case's design decisions start with the suitable robot, the suitable chatting model, identifying common problems that cause failures, identifying potential solutions, and planning continuous improvement. In conclusion, it is recommended to use a closed-loop control algorithm that guides the use of trained Artificial Intelligence (AI) pre-trained models and provides vocabulary filtering, re-train batched models on new datasets, learn online from data streams, and/or use reinforcement learning models to self-update the trained models and reduce errors.

Original language	English
Number of pages	4
DOIs	https://doi.org/10.48550/arXiv.2309.03708
Publication status	Published - 19 Jun 2023
Event	5th International ACM Conference on Conversational User Interfaces (CUI) 2023 - Eindhoven, Netherlands Duration: 19 Jul 2023 → 21 Jul 2023 Conference number: 5 https://cui.acm.org/2023/

Conference

Conference	5th International ACM Conference on Conversational User Interfaces (CUI) 2023
Abbreviated title	WTF/CUI 2023
Country/Territory	Netherlands
City	Eindhoven
Period	19/07/23 → 21/07/23
Internet address	https://cui.acm.org/2023/

Keywords

Human-Computer Interaction (cs.HC)
Robotics (cs.RO)
Machine Learning (cs.LG)

Access to Document

10.48550/arXiv.2309.03708Licence: CC BY

Cite this

@conference{0e79da5c61a14554892da26013a04335,

title = "Chat Failures and Troubles: Reasons and Solutions",

abstract = "This paper examines some common problems in Human-Robot Interaction (HRI) causing failures and troubles in Chat. A given use case's design decisions start with the suitable robot, the suitable chatting model, identifying common problems that cause failures, identifying potential solutions, and planning continuous improvement. In conclusion, it is recommended to use a closed-loop control algorithm that guides the use of trained Artificial Intelligence (AI) pre-trained models and provides vocabulary filtering, re-train batched models on new datasets, learn online from data streams, and/or use reinforcement learning models to self-update the trained models and reduce errors. ",

keywords = "Human-Computer Interaction (cs.HC), Robotics (cs.RO), Machine Learning (cs.LG)",

author = "Manal Helal and Patrick Holthaus and Gabriella Lakatos and Farshid Amirabdollahian",

note = "{\textcopyright} 2023 The owner/author(s).; 5th International ACM Conference on Conversational User Interfaces (CUI) 2023, WTF/CUI 2023 ; Conference date: 19-07-2023 Through 21-07-2023",

year = "2023",

month = jun,

day = "19",

doi = "10.48550/arXiv.2309.03708",

language = "English",

url = "https://cui.acm.org/2023/",

}

TY - CONF

T1 - Chat Failures and Troubles: Reasons and Solutions

AU - Helal, Manal

AU - Holthaus, Patrick

AU - Lakatos, Gabriella

AU - Amirabdollahian, Farshid

N1 - Conference code: 5

PY - 2023/6/19

Y1 - 2023/6/19

N2 - This paper examines some common problems in Human-Robot Interaction (HRI) causing failures and troubles in Chat. A given use case's design decisions start with the suitable robot, the suitable chatting model, identifying common problems that cause failures, identifying potential solutions, and planning continuous improvement. In conclusion, it is recommended to use a closed-loop control algorithm that guides the use of trained Artificial Intelligence (AI) pre-trained models and provides vocabulary filtering, re-train batched models on new datasets, learn online from data streams, and/or use reinforcement learning models to self-update the trained models and reduce errors.

AB - This paper examines some common problems in Human-Robot Interaction (HRI) causing failures and troubles in Chat. A given use case's design decisions start with the suitable robot, the suitable chatting model, identifying common problems that cause failures, identifying potential solutions, and planning continuous improvement. In conclusion, it is recommended to use a closed-loop control algorithm that guides the use of trained Artificial Intelligence (AI) pre-trained models and provides vocabulary filtering, re-train batched models on new datasets, learn online from data streams, and/or use reinforcement learning models to self-update the trained models and reduce errors.

KW - Human-Computer Interaction (cs.HC)

KW - Robotics (cs.RO)

KW - Machine Learning (cs.LG)

U2 - 10.48550/arXiv.2309.03708

DO - 10.48550/arXiv.2309.03708

M3 - Paper

T2 - 5th International ACM Conference on Conversational User Interfaces (CUI) 2023

Y2 - 19 July 2023 through 21 July 2023

ER -

Chat Failures and Troubles: Reasons and Solutions

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this