Chatbots

11 Key excerpts on "Chatbots"

• 

  eBook - PDF

  Human-Computer Interaction

  • Inaki Maurtua(Author)
  • 2009(Publication Date)
  • IntechOpen

    (Publisher)

  This allows the program to produce relevant responses to human utterances in natural language form. As such, it represents a particular style of intelligent agent, most commonly known as a Chatbot (or Chatterbot). It is this aspect of NLP agents as Chatbots that is the concern of this paper. In theory, a powerful enough Chatbot could offer a hugely attractive form of Human Computer Interaction in that computer use could be mediated by an agent that behaves as though it can understand instructions that are typed in by human users and respond in kind with natural-seeming utterances. The point has been raised that in order to communicate with computers, humans must learn the language of computers and that computers are, at present, incapable of communicating by using human languages (Pinker: 2004). The prospect of an Chatbot that is powerful enough to deal with human languages would radically change this state of affairs. There are several ways of approaching the problem of building a software engine that has to deal with human language utterances. Since an agent that is successful in this task is essentially a form of Artificial Intelligence, it seems fitting to begin by describing the 9 Human-Computer Interaction 146 traditional approach to AI and how it relates to this problem. Traditional AI approaches rely on a Strong Physical Symbols System approach (SPSS), whereby a series of symbols is given to the engine in question, the symbols are manipulated in some logical manner within the engine and a series of symbols is given as output (Newell and Simon; 1976). For language systems such as Chatbots, this would involve arming the program with certain rules about grammar and word meanings. The system relies on manipulating these rules to derive meaning from incoming information and to then construct responses.

  Sign up to read

  Learn more about book
• 

  No longer available |Learn more

  Hands-On Machine Learning on Google Cloud Platform

  • Giuseppe Ciaburro, V Kishore Ayyadevara, Alexis Perrier(Authors)
  • 2018(Publication Date)
  • Packt Publishing

    (Publisher)

  Chatbots

  The era of Chatbots has now arrived, a new technological phenomenon that has helped generate a new way of interacting with machines, consequently creating businesses. Chatbots are robots that interact with users through a chat and are able to assist them by carrying out extremely limited tasks: providing information on a current account, buying a ticket, receiving news about the weather, and so on.

  A chatbot processes the text presented by the user, before responding based on a complex set of algorithms that interpret and identify what the user has said. After deducting what the user requires, it determines a set of appropriate responses based on the information extracted from the context. Some Chatbots offer an extraordinarily authentic conversational experience, in which it is very difficult to determine if the agent is a bot or a human being.

  Chatbots are also one of the most exciting innovations brought about by AI. In this chapter, after introducing the main concepts on which all of this technology is based, we will present the methods for building contextual Chatbots and implement a simple chatbot end-to-end application on GCP.

  Topics covered:

  • Chatbot fundamentals
  • Chatbot design techniques
  • Natural language processing
  • Google Cloud Dialogflow
  • Chatbot building and implementation on GCP

  At the end of the chapter, the reader will have completed a hands-on introduction to Chatbots and learned how to train a contextual chatbot while implementing it in a real web application.

  Passage contains an image

  Chatbots fundamentals

  Chat bots, or Chatbots, are programs that can interact through a chat with a human being, simulating their behavior. A conversation is then established between the human and the robot. Since the first developments in computer science, in collaboration with other disciplines, scholars have tried to reproduce typically human cognitive processes through the use of machines. They are usually used for simple and repetitive activities, which may otherwise take a lot of time or which are not worth assigning a human resource.

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Artificial Intelligence in Higher Education

  A Practical Approach

  • Prathamesh Padmakar Churi, Shubham Joshi, Mohamed Elhoseny, Amina Omrane, Prathamesh Padmakar Churi, Shubham Joshi, Mohamed Elhoseny, Amina Omrane(Authors)
  • 2022(Publication Date)
  • CRC Press

    (Publisher)

  4   Chatbots in Education A Systematic Review of the Science Literature Antonio-José Moreno-Guerrero, José-Antonio Marín-Marín, Pablo Dúo-Terrón and Jesús López-Belmonte

  DOI: 10.1201/9781003184157-4

  CONTENTS

  4.1 Introduction: Background and Driving Forces 4.2 Justification and Applied Research Method 4.3 Results of the Systematic Literature Review 4.4 Discussion and Conclusions References

  4.1 Introduction: Background and Driving Forces

  A chatbot is considered a computer programme that is able to hold a conversation with a human person, making use of technology based on Artificial Intelligence software (Touimi et al., 2020 ). This type of resource is integrated in various types of programmes that are commonly used on a daily basis. An example of this is Facebook or Telegram (Shumanov & Johnson, 2021 ). These platforms provide Chatbots that try to answer various questions automatically, responding to the needs of the interlocutor (Rajaobelina & Ricard, 2021 ). A chatbot can be considered a powerful and useful tool, since it shares information and solves doubts (Abd-Alrazaq et al., 2021 ).

  Among the characteristics that stand out in Chatbots are agility of response and ability to learn (Tsai et al., 2021 ). That is, they are able to respond to interlocutors’ queries quickly and concisely. Moreover, they are able to learn while interacting with people (Flanagan & Walker, 2020 ). They adapt their responses to the real needs of the interlocutors. This is because their foundations are based on Artificial Intelligence—specifically, machine learning, big data and natural language processing (Wang et al., 2020

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Knowledge Engineering for Modern Information Systems

  Methods, Models and Tools

  • Anand Sharma, Sandeep Kautish, Prateek Agrawal, Vishu Madaan, Charu Gupta, Saurav Nanda, Anand Sharma, Sandeep Kautish, Prateek Agrawal, Vishu Madaan, Charu Gupta, Saurav Nanda(Authors)
  • 2022(Publication Date)
  • De Gruyter

    (Publisher)

  Now, this is just a simple example of how ML could work. Here, some bots are designed for specific purposes where you can ask only those questions. For example, you are designing a bot for your college, and you ask something regarding movies, it will not be able to answer because that bot is not trained for that. During the development, the phrases are designed to help the bot understand the context and infer responses from user inputs.

  Every query and every statement we enter into the chat box is helping the bot to become more intelligent and more efficient the more it is used and indirectly getting trained. The more we use, the more familiar we become and also get to know the problems too. And depending on the response, new features can also be added.

  Chatbots with machine learning: building neural conversational agents

  Interacting with the machine with the help of natural language is one of the requirements. This field is called Chatbots as we expect the machine to provide us an informative or most accurate answer, which is not more different from the human. That means the answer or the response must be accurately equal to the typical human response for that particular question.

  There are two significant types of dialogue systems: goal-oriented and general conversation. Goal-oriented is Siri, Alexa, Cortana, and so on, and general conversation is Microsoft Tay bot.

  This helps people to solve everyday problems using natural language, while the latter attempts to talk with people on a wide range of topics.

  8  Natural language processing

  NLP is a subdivision or a part of AI, which fundamentally deals with the interaction between the human and the computer by using natural language. The superlative objective of NLP is to read, decrypt or extract, understand, and be coherent of the language that humans will use to interact with the machine in such a manner that it seems that the human interacts with another human instead of the human interacting with the computer. Primarily, NLP is being used for interactions such as a human interacting with the machine; machine that would be able to catch and reproduce audio; text-to-voice and voice-to-text conversion; processing of text that will be input into the machine; majorly, a machine that interacts with the human with audio along with the text and many more. Nowadays, NLP is also used so that a dummy human video is placed that interacts with the users of the chatbot and acts as human-to-­human interaction instead of human-to-machine interaction. Translation of languages like Google Translate, word processor applications such as Grammarly or Microsoft Word for checking grammatical accuracy of the texts that are typed in those applications are some significant applications of NLP. They can be found in call centers to automate the response to user’s queries such as interactive voice response and can extensively be used in applications that act as personal assistant such as Google Assistant, which responds to the user when the user utters OK Google; Siri, a personal assistant in iOS devices; Cortana; Alexa; and more.

  Sign up to read

  Learn more about book
• 

  eBook - PDF

  Swarm Intelligence

  • Russell C. Eberhart, Yuhui Shi, James Kennedy(Authors)
  • 2001(Publication Date)
  • Morgan Kaufmann

    (Publisher)

  A message is inter-preted by the receiver according to its own inner “deep” structures and constraints. An interesting minor tradition in artificial intelligence shows the po-tential, though, for a “shallow” view of language processing and interac-tion between humans and computers. Chatterbots are programs whose specialty is real-time verbal interaction with human users. Some chatter-bots are connected to knowledge sources such as databases on particular topics, but their real strength, what makes them different from any other database-querying program, is their ability to deliver natural-sounding responses to questions and conversational comments. The most com-monly seen chatterbot application is implemented in a chat room or MUD environment, where the bot might show newcomers around, an-swer questions and provide information, strike up conversations with people, or make a general nuisance of itself. Recall that the Turing test defined computer intelligence in terms of social interaction; a computer that could interact with a human in such a manner that the user could not tell whether it was a machine or a person Shallow Understanding 125 was considered to be able to think, according to Turing. This classic definition conspicuously fails to mention aspects of “deep processing,” but rather focuses on lifelike, anthropomorphic communication. We suspect that this was a profoundly insightful move on Turing’s part. It is part of our positive self-image, especially for us intellectual types who play with sophisticated toys, to see our minds, our understanding of the world, as something deep, mysterious, profound. Computer programs that process complex databases of information, drawing profound con-clusions, proving theorems, finding logical contradictions in convoluted inferential arguments—these seem “deep.” Programs that can make small talk and silly jokes do not seem deep; we have heard them referred to as “shallow AI.” They are also a lot harder to write.

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Conversational Artificial Intelligence

  • Romil Rawat, Rajesh Kumar Chakrawarti, Sanjaya Kumar Sarangi, Anand Rajavat, Mary Sowjanya Alamanda, Kotagiri Srividya, K. Sakthidasan Sankaran, Piyush Vyas(Authors)
  • 2024(Publication Date)
  • Wiley-Scrivener

    (Publisher)

  Figure 39.2 .

  Conversational AI has entered a new phase thanks to the rapid development of natural language processing (NLP) technology, which has profoundly altered the ways in which humans engage with machines [9] . Thanks to recent developments in machine learning and language comprehension, Chatbots powered by NLP have emerged as important instruments in molding this new environment. These smart Chatbots can both comprehend and produce natural-sounding dialogue, making it difficult to discern whether you are talking to a real person or a computer. The use cases and consequences of NLP-driven Chatbots in the field of conversational artificial intelligence are investigated in depth in this research study [10] . Chatbots, which combine natural language processing methods with software development methodologies, have proliferated across industries and are reshaping everything from customer service to business operations to consumer engagement. NLP-driven Chatbots have proven their capacity to provide real-time assistance, automate processes, and increase engagement across a wide range of use cases, from personalized customer service interactions to healthcare diagnostics to e-commerce recommendations to educational support. Rapid adoption of natural language processing-driven Chatbots, however, brings with it a number of ethical, cultural, and practical difficulties [11] . Important considerations about the ethical use of these technologies arise in the context of concerns about privacy, data security, algorithmic fairness, and the potential displacement of human positions in the workforce. To ensure the successful and ethical integration of NLP-driven Chatbots into our daily lives, it is crucial to strike a balance between maximizing their benefits and resolving these problems. This study paper attempts to provide a thorough grasp of the complex terrain of NLP-driven Chatbots through a methodical examination of real-world applications, ethical frameworks, and future trends [12] . We hope to contribute to an informed discussion on the role of NLP-driven Chatbots in determining the future of conversational AI by diving into both their transformative potential and the difficult considerations they bring out. The major objective is to conduct an in-depth analysis of NLP-driven Chatbots in conversational AI and their potential applications and ramifications [13]

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Artificial Intelligence with Python

  Your complete guide to building intelligent apps using Python 3.x and TensorFlow 2, 2nd Edition

  • Alberto Artasanchez, Prateek Joshi(Authors)
  • 2020(Publication Date)
  • Packt Publishing

    (Publisher)

  Chatbots today are still somewhat narrow. As many things as we can do with Alexa, Siri, and Google Home, currently, they can only help us with specific tasks. They cannot yet handle certain human traits very well like empathy, sarcasm, and critical thinking. In their current state, Chatbots will be able to help us with repetitive transactional tasks in a more human-centered way.

  However, even though we should try to keep our chatbot as tight as possible on domain, that doesn't mean that we shouldn't try to inject a little "personality" into our bot. Alexa can be cheeky and humorous at times and you should strive for the same with your bots. This should result in higher engagement with your bot.

  While chatting, people typically expect a certain level of mutual interest in the conversation and, consequently, that the conversation will take place in such a way that there will be answers that feed the subsequent questions, as well as answers that inform and promote the conversation. Using a little bit of slang will go a long way to making your bot more realistic and engaging.

  Before we delve into the design of our own chatbot, let's cover some foundational concepts that will help us during development.

  Chatbot concepts

  Before we develop our code, let's set a baseline and visit some useful definitions related to Chatbots. Agent

  An agent is a system that can handle all the conversations and route all the necessary actions. It is a natural-language understanding module that gets trained frequently to cater to use-specific requirements.

  Intents When two people communicate, they both have a reason as to why they started the communication. It might be as simple as catching up with a friend and finding out what they have been doing. It could be that one of them is trying to sell something and so forth. These "intents" fall under three broad classifications:

  • The speaker is trying to entertain – An example is when someone tells you a joke.
  • The speaker is trying to inform – Someone asks what time is it, or, what is the temperature? And they receive the answer.
  • The speaker is trying to persuade – The agenda is to try to sell something.

  For most Chatbots, their role is to fulfill commands and perform tasks. For this reason, the first task they need to perform is to ascertain the intent of the person that invoked them. Intents have elements such as context, training phase, actions and parameters, and responses.

  Sign up to read

  Learn more about book
• 

  eBook - PDF

  Conversational AI

  Dialogue Systems, Conversational Agents, and Chatbots

  • Michael McTear(Author)
  • 2022(Publication Date)
  • Springer

    (Publisher)

  One of the advantages of Chatbots is that they can run on messaging applications such as Facebook Messenger, Telegram, Slack, Skype, Line, and WhatsApp that are widely used by millions of people to interact with friends, colleagues, and the services of companies. This means that it is not necessary to download and install a different app for each new service. Fur- thermore, since Chatbots live within messaging applications, there is no need to worry about platform issues, as each chatbot can be available on all operating systems that are supported by the messaging app. In contrast, native mobile apps have to be adapted or rewritten for each mobile operating system and they need to be frequently updated to keep up with upgrades to the host system and its features. Since Chatbots are implemented server-side, any updates can be propagated almost immediately to all users. The chatbot interface is similar to text messag- ing (SMS), except that the interaction takes place synchronously in real time and the other participant in the conversation is a chatbot and not a human. Generally, chatbot dialogues on messaging platforms are system-led and the user’s responses are often limited to clicking on but- tons containing pre-defined words and phrases (known as Quick Replies or Suggestion Chips). In 1.3. PRESENT-DAY DIALOGUE SYSTEMS 25 Figure 1.1: A chatbot with Quick Replies. Used with permission. some cases the user can also type in a few words from a fixed set of possible inputs. Figure 1.1 shows an example from the iHelpr chatbot that provides guided self-assessment and advice in areas of mental health [Cameron et al., 2018]. Natural Language Understanding (NLU) can be used in more advanced systems to interpret the user’s free text inputs, giving the user the op- portunity to “say what they want and how they want”, without being restricted to a fixed set of commands or queries.

  Sign up to read

  Learn more about book
• 

  eBook - PDF

  Human Robot Interaction

  • Nilanjan Sarkar(Author)
  • 2007(Publication Date)
  • IntechOpen

    (Publisher)

  5 Robots That Learn Language: A Developmental Approach to Situated Human-Robot Conversations Naoto Iwahashi National Institute of Information and Communications Technology, Advanced Telecommunications Research Institute International Japan 1. Introduction Recent progress in sensor technologies and in an infrastructure for ubiquitous computing has enabled robots to sense physical environments as well as the behaviour of users. In the near future, robots that change their behaviour in response to the situation in order to support human activities in everyday life will be increasingly common, so they should feature personally situated multimodal interfaces. One of the essential features of such interfaces is the ability of the robot to share experiences with the user in the physical world. This ability should be considered in terms of spoken language communication, which is one of the most natural interfaces. The process of human communication is based on certain beliefs shared by those communicating (Sperber & Wilson, 1995). Language is one such shared belief and is used to convey meaning based on its relevance to other shared beliefs. These shared beliefs are formed through interaction with the environment and other people, and the meaning of utterances is embedded in such shared experiences. From this viewpoint, spoken language interfaces are important not only because they enable hands-free interaction but also because of the nature of language, which inherently conveys meaning based on shared experiences. For people to take advantage of such interfaces, language processing methods must make it possible to reflect shared experiences. However, existing language processing methods, which are characterized by fixed linguistic knowledge, do not make this possible (Allen et al., 2001). In these methods, information is represented and processed by symbols whose meaning has been predefined by the machines' developers.

  Sign up to read

  Learn more about book
• 

  eBook - PDF

  Proceedings of the IWEMB 2019

  Third International Workshop on Entrepreneurship in Electronic and Mobile Business

  • Stephan Böhm, Sid Suntrayuth, Stephan Böhm, Sid Suntrayuth(Authors)
  • 2020(Publication Date)
  • Books on Demand

    (Publisher)

  2. Research Background 2.1 Recruiting Chatbots Chatbots are applied in many different areas within business contexts now that people’s way of communication changed from unidirectional inquiries to forms of dialogues. Chatbot technology concerns all kinds of stakeholders and users from every sector and almost all industries. Drift et al. (2018) 215 found that 15 percent of US surveyed adults ( N = 1,051) already commu-nicated with businesses via Chatbots. Drivers of Chatbots usage revealed by the same study are: (1) a perceived difficulty in traditional website naviga-tion, (2) a lack of sufficient answers to simple questions, (3) problems to find detailed information and (4) time expenditure to find the service of interest (Drift et al., 2018). People especially value Chatbots for their 24-hour service, the instant responses, the answers to questions, and the easy way of communications. Main areas of application are quick answers to simple questions and access to the search for information, for example in emergencies, resolving (technical) problems and complaints, receiving de-tails and explanations (e.g., payment or delivery information in web shops), consultancy, finding the right human customer service authority to talk to or making a reservation for example (Drift et al., 2018; Fittkau & Maaß Consulting, 2017). Twenty-seven percent of the aforementioned US citi-zens can even imagine using a chatbot for paying bills (Drift et al., 2018). In the context of HR, Chatbots can generally support all recruiting pro-cess steps. Such HR-related tasks are, for example, (1) job profile position-ing, (2) job search, (3) the application phase, (4) candidate pre-selection, (5) detailed candidate selection and (6) hiring.

  Sign up to read

  Learn more about book
• 

  eBook - PDF

  Robots Unlimited

  Life in a Virtual Age

  • David Levy(Author)
  • 2005(Publication Date)
  • A K Peters/CRC Press

    (Publisher)

  -7 -How Computers Communicate Natural Language Processing Natural Language Processing (NLP 1 ) is the branch of Artificial Intelli-gence concerned with enabling computers to talk like you and me, to understand what is said to them, to be able to conduct sensible conver-sations and even to translate into and out of foreign languages. When computers can understand what we mean when we speak or type some-thing in English or in any other natural language, they will be much easier to use and will fit in more with our everyday lives. That is why, ever since Alan Turing first described, in 1950, what is now known as the Turing Test, this challenge has been widely regarded as the touchstone of AI. But the goal of having computers engage in intelligent conversation appears to be almost as elusive now as it was then. Some of the Problems in NLP Why is this task so hard? After all, our children can make more sense in their conversation at the age of three or four than can the biggest, most powerful computers of today, even when running software that is the product of tens of thousands of person-years of research or more. The resources that have been applied to NLP exceed many times over the resources that have been applied to computer Chess, and this includes some of the brightest minds on our planet, not only from the field of computer science but also from linguistics, mathematics, statistics, psy-chology and other areas of cognitive science. But despite all this effort, while a program can defeat the world’s strongest Chess player, no pro-gram can conduct even a half-hour long conversation at the level of a high school freshman.

  Sign up to read

  Learn more about book