Models towards a hybrid conversational agent for contact centres

Sankar, Gopal Ravi; Greyling, Jean; Vogts, Dieter; Plessis, Mathys C. du

doi:10.1145/1456659.1456683

Cited by 5 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…-Usefulness: which states that the answer (provided by the bot) should include all the information that answers the question clearly and concisely [54,40]. -Speed: which states that the answer should be returned in a time that is faster than the traditional way that a developer retrieves information [54].…”

Section: Evaluating the Botmentioning

confidence: 99%

MSRBot: Using bots to answer questions from software repositories

Abdellatif¹,

Badran²,

Shihab³

2020

Empir Software Eng

View full text Add to dashboard Cite

Software repositories contain a plethora of useful information that can be used to enhance software projects. Prior work has leveraged repository data to improve many aspects of the software development process, such as, help extract requirement decisions, identify potentially defective code and improve maintenance and evolution. However, in many cases, practitioners are not able to fully benefit from software repositories due to the fact that they need special expertise and dedicated effort to mine their repositories.Therefore, in this paper, we use bots to automate and ease the process of extracting useful information from software repositories. Particularly, we lay out an approach of how bots, layered on top of software repositories, can be used to answer some of the most common software development/maintenance questions facing developers. We perform a preliminary study with 12 participants to validate the effectiveness of the bot. Our findings indicate that using bots achieves very promising results in terms of answer accuracy, speed and usefulness. Our work has the potential to transform the MSR field by significantly lowering the barrier to entry, making the extraction of useful information from software repositories as easy as chatting with a bot.

show abstract

Section: Evaluating the Botmentioning

confidence: 99%

MSRBot: Using bots to answer questions from software repositories

Abdellatif¹,

Badran²,

Shihab³

2020

Empir Software Eng

View full text Add to dashboard Cite

show abstract

“…to set or retrieve the user's address for the system's back-end) Internet Computer Entity) architecture 2 and its siblings (Sankar, Greyling, Vogts, & du Plessis, 2008).…”

Section: Artificial Intelligence Markup Language (Aiml)mentioning

confidence: 99%

“…• The main measure considered is the user satisfaction (US) metric that estimates (e.g., in a scale of 1 to 5) the impression a system made on end users (Sankar et al, 2008). It is usually collected as follows: (a) obtain numbers via user surveys and (b) consider a (statistically) representative sample of users.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…A single AIML file can be used to specify all system‐user interactions or turns and can be crafted for any application domain. AIML has become a de facto standard for developing simple chatbots and has given rise to a number of chatbot open source APIs, among which the ALICE (Artificial Linguistic Internet Computer Entity) architecture and its siblings (Sankar, Greyling, Vogts, & du Plessis, ).…”

Section: Troubleshooting Chatbotsmentioning

confidence: 99%

See 1 more Smart Citation

Chatbots for troubleshooting: A survey

Thorne

2017

Language and Linguist. Compass

View full text Add to dashboard Cite

Chatbots are artificial agents designed to engage in textbased conversations (chats) with end users. They can be seen as a restricted kind of dialog system that deals with written rather than spoken language. They have been an object of research in academia and industry since the early days of artificial intelligence and computational linguistics. This paper intends to survey a specific subtype of chatbots, troubleshooting chatbots, which are chatbots that aim at automating troubleshooting contact centers and services. Troubleshooting chatbots have inspired considerable interest in industry due to their cost savings potential.

show abstract

“…Computers need some sort of interaction in order to perform a specific goal or task. Natural language is one of many interface styles that can be used in the dialogue between a human user and a computer through the use of speech or text [4]. Chatbot is a technology that makes interaction between human and machine using natural language possible [5].…”

mentioning

confidence: 99%

Ugleo: A Web Based Intelligence Chatbot for Student Admission Portal Using Megahal Style

Siswadi

Tarigan

2018

infokom

View full text Add to dashboard Cite

To fulfill the prospective student's information need about student admission, Gunadarma University has already many kinds of services which are time limited, such as website, book, registration place, Media Information Center, and Question Answering’s website (UG-Pedia). It needs a service that can serve them anytime and anywhere. Therefore, this research is developing the UGLeo as a web based QA intelligence chatbot application for Gunadarma University's student admission portal. UGLeo is developed by MegaHal style which implements the Markov Chain method. In this research, there are some modifications in MegaHal style, those modifications are the structure of natural language processing and the structure of database. The accuracy of UGLeo reply is 65%. However, to increase the accuracy there are some improvements to be applied in UGLeo system, both improvement in natural language processing and improvement in MegaHal style.

show abstract

Models towards a hybrid conversational agent for contact centres

Cited by 5 publications

References 3 publications

MSRBot: Using bots to answer questions from software repositories

MSRBot: Using bots to answer questions from software repositories

Chatbots for troubleshooting: A survey

Ugleo: A Web Based Intelligence Chatbot for Student Admission Portal Using Megahal Style

Contact Info

Product

Resources

About