Google DialogFlow Research Articles

Chatbot integrated with machine learning deployed in the cloud and performance evaluation

Recently human-machine digital assistants gained popularity and commonly used in question-and-answer applications and similar consumer-supporting domains. A class of more sophisticated digital assistants employing longer dialogs follow the trend, and there are several commercial platforms supporting their prototyping such as Google DialogFlow, Manychat, Chatfuel, Amazon Lex, etc. This paper explores cloud deployment of chatbots systems and their performance assessment methodologies. The performance measures includes system response delays and natural language processing capabilities. A case study platform supporting so-called deep-logic chatbots with long cycling capabilities is implemented and used for the assessment. To enable human-like conversations with a chatbot, huge training data, complex natural language understanding models are required and need to be adjusted and trained continuously. We explore implementation formats supporting auto scaling, and uninterrupted availability. In particular, we employ an architecture consisting of separate dialog management, authentication, and Natural Language Understanding (NLU) services. Finally, we present a performance evaluation of such loosely coupled chatbot system. Keywords: Cloud Deployment, Natural language understanding, Chatbot, Performance assessment

Development of an AI Chatbot-Based Teaching Model for English Picture Book Retelling Activities

The aim of this study was to develop and apply an AI chatbot-based teaching model for English picture book retelling activities in elementary schools. Participants were 18 students of the 5th grade who performed the retelling activity with three English picture books. AI chatbots were built with Google Dialogflow API. The criteria for building them were developed based on previous studies. Results are as follows. First, the model was composed of two lesson periods. In the first period, learners read the story together and checked their comprehension. In the next period, a teacher modelled retelling to students and the AI chatbots mediated learners’ retelling by asking questions. Finally, learners independently retold the story. Second, the criteria consisted of linguistic and affective perspectives, with four elements for each. Finally, students’ productions showed that the design of the chatbots’ prompts and scaffoldings partially affected students’ production. Moreover, the chatbots’ utterances should be sophisticatedly designed according to learners’ levels to gradually elicit their productions. This study suggests that integrating AI chatbots into classrooms can mediate young learners’ story retelling to partially support instructors who teach English reading skills in regular classes.

Integration of NLP and Speech-to-text Applications with Chatbots

With the evolving artificial intelligence technology, the chatbots are becoming smarter and faster lately. Chatbots are typically available round the clock providing continuous support and services. A chatbot or a conversational agent is a program or software that can communicate using natural language with humans. The challenge of developing an intelligent chatbot still exists ever since the onset of artificial intelligence. The functionality of chatbots can range from business oriented short conversations to healthcare intervention based longer conversations. However, the primary role that the chatbots have to play is in understanding human utterances in order to respond appropriately. To that end, there is an increased emergence of Natural Language Understanding (NLU) engines by popular cloud service providers. The NLU services identify entities and intents from the user utterances provided as input. Thus, in order to integrate such understanding to a chatbot, this paper presents a study on existing major NLU platforms. Then, we present a case study chatbot integrated with Google DialogFlow and IBM Watson NLU services and discuss their intent recognition performance.

A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering

Chatbots are envisioned to dramatically change the future of Software Engineering, allowing practitioners to chat and inquire about their software projects and interact with different services using natural language. At the heart of every chatbot is a Natural Language Understanding (NLU) component that enables the chatbot to understand natural language input. Recently, many NLU platforms were provided to serve as an off-the-shelf NLU component for chatbots, however, selecting the best NLU for Software Engineering chatbots remains an open challenge. Therefore, in this paper, we evaluate four of the most commonly used NLUs, namely IBM Watson, Google Dialogflow, Rasa, and Microsoft LUIS to shed light on which NLU should be used in Software Engineering based chatbots. Specifically, we examine the NLUs' performance in classifying intents, confidence scores stability, and extracting entities. To evaluate the NLUs, we use two datasets that reflect two common tasks performed by Software Engineering practitioners, 1) the task of chatting with the chatbot to ask questions about software repositories 2) the task of asking development questions on Q&A forums (e.g., Stack Overflow). According to our findings, IBM Watson is the best performing NLU when considering the three aspects (intents classification, confidence scores, and entity extraction). However, the results from each individual aspect show that, in intents classification, IBM Watson performs the best with an F1-measure > 84%, but in confidence scores, Rasa comes on top with a median confidence score higher than 0.91. Our results also show that all NLUs, except for Dialogflow, generally provide trustable confidence scores. For entity extraction, Microsoft LUIS and IBM Watson outperform other NLUs in the two SE tasks. Our results provide guidance to software engineering practitioners when deciding which NLU to use in their chatbots.

A Voice Based Assistant Using Google Dialogflow and Machine Learning

Virtual Personal Assistant (VPA) is one of the most successful results of Artificial Intelligence, which has given a new way for the human to have its work done from a machine. This paper gives a brief survey on the methodologies and concepts used in making of an Virtual Personal Assistant (VPA) and thereby going on to use it in different software applications. Speech Recognition Systems, also known as Automatic Speech Recognition (ASR), plays An important role in virtual assistants in order to help user have a conversation with the system. In this project, we are trying to make a Virtual Personal Assistant ERAA which will include the important features that could help in assisting ones’ needs. Keeping in mind the user experience, we will make it as appealing as possible, just like other VPAs. Various Natural Language Understanding Platforms like IBM Watson and Google Dialogflow were studied for the same. In our project, we have used Google Dialogflow as the NLU Platform for the implementation of the software application. The User-Interface for the application is designed with the help of Flutter Software Platform. All the models used for this VPA will be designed in a way to work as efficient as possible. Some of the common features which are available in most of the VPAs will be added. We will be implementing ERAA via a smartphone application, and for future scope, our aim will be to implement it on the desktop environment. The following Paper ensure to provide the methodologies used for development of the application. It provides the obtained outcomes of the features developed within the application. It shows how the available natural language understanding platforms can reduce the burden of the user, and therefore going on to develop a robust software application.

Visual design of dialogue flows for conversational interfaces

ABSTRACT Nowadays, new technologies are taking place for enabling conversational interactions between users and bots. Creating conversational interfaces (CI) paves the way for new design challenges. Designers need to use appropriate design specifications for creating a logically sound dialogue endowed with proper visual cues in the case of chatbots that captures the entire user experience. To do it they need the help of domain experts. Experts in mobility, environment, energy, e-health, weather, etc., are the only ones who well-know the specific domain in which the bot will act. Current tools used to design interactive flows of dialogue entail deep programming skills their users need to know. Starting from this consideration, the paper proposes a design environment that offers experts the possibility to design a flow of dialogue without getting lost in technicalities. By using visual language, the expert can specify intents, actions, entities and parameters at the base of the flow of dialogue on which the bot will be created. Then, our engine automatically translates into a bot compliant with the Google DialogFlow technology. Finally, the paper present a preliminary analysis of the system carried out to test its features and how these are reflected in its ease of use.

PENGEMBANGAN APLIKASI QnA UNTUK PENDAFTARAN MAHASISWA BARU STMIK AKAKOM

STMIK AKAKOM annually opens new student registration through offline and online media. Through online media, several media such as websites, social media and email are used. However, on media such as social media, there are questions that often arise regarding new student registration information. With limited human resources to always be online for 24 hours, an alternative model is needed to provide answers to these questions, even though the social media manager offline. Nowadays. In the term of technological developments, it is possible to create a model of knowledge base in the form of a summary of questions and answers to certain topics. This knowledge base can use as a model for creating a prototype application that can provide answers if there are questions related to new student registration. This study aims to provide convenience in the question and answer process by using a Google Dialogflow.

Interactive Health Information Chatbot for Non-Communicable Diseases in Swahili Language

Current health awareness campaign strategies, efforts, and methods on NCDs have not produced improved outcomes in reducing the burden, spread, and deaths linked to NCDs in Tanzania. To support, compliment, and improve health literacy on NCDs and promote good healthcare, we designed and developed an interactive health Chatbot ‘afyaBot’ in Swahili language that can respond to user's requests concerning NCDs symptoms, prevention, management, and cure. The Chatbot was designed using Botsociety; a special tool for designing Chatbot prototypes; BotMan framework for coding the Chatbot logic and Google Dialogflow platform that offers high-level Natural Language Processing capabilities. The Chatbot was integrated into the Facebook Messenger platform which offers free public API access that eliminates the cost of the internet from the consumers. The Chatbot was tested for accuracy, usability, user experience, responsiveness, reliability, maintainability, and portability. The results of implementation were satisfactory and provide insights useful to stakeholders in the health sector. The interactive Chatbot was designed to provide real-time information on NCDs, create awareness, and educate users on preventive, control, and treatment measures of NCDs. It will likewise assist healthcare providers to collect accurate timely health data for monitoring, planning, and research purpose.

Explainable Artificial Intelligence Recommendation System by Leveraging the Semantics of Adverse Childhood Experiences: Proof-of-Concept Prototype Development.

BackgroundThe study of adverse childhood experiences and their consequences has emerged over the past 20 years. Although the conclusions from these studies are available, the same is not true of the data. Accordingly, it is a complex problem to build a training set and develop machine-learning models from these studies. Classic machine learning and artificial intelligence techniques cannot provide a full scientific understanding of the inner workings of the underlying models. This raises credibility issues due to the lack of transparency and generalizability. Explainable artificial intelligence is an emerging approach for promoting credibility, accountability, and trust in mission-critical areas such as medicine by combining machine-learning approaches with explanatory techniques that explicitly show what the decision criteria are and why (or how) they have been established. Hence, thinking about how machine learning could benefit from knowledge graphs that combine “common sense” knowledge as well as semantic reasoning and causality models is a potential solution to this problem.ObjectiveIn this study, we aimed to leverage explainable artificial intelligence, and propose a proof-of-concept prototype for a knowledge-driven evidence-based recommendation system to improve mental health surveillance.MethodsWe used concepts from an ontology that we have developed to build and train a question-answering agent using the Google DialogFlow engine. In addition to the question-answering agent, the initial prototype includes knowledge graph generation and recommendation components that leverage third-party graph technology.ResultsTo showcase the framework functionalities, we here present a prototype design and demonstrate the main features through four use case scenarios motivated by an initiative currently implemented at a children’s hospital in Memphis, Tennessee. Ongoing development of the prototype requires implementing an optimization algorithm of the recommendations, incorporating a privacy layer through a personal health library, and conducting a clinical trial to assess both usability and usefulness of the implementation.ConclusionsThis semantic-driven explainable artificial intelligence prototype can enhance health care practitioners’ ability to provide explanations for the decisions they make.

A Review on Implementation Issues of Rule-based Chatbot Systems

Communication between a human and computer is area of interest for many researchers since past many years. There are different ways to perform the communication between human and computers. Chatbots have become popular mechanism to perform such communication. Chatbot is a computer program which makes this interaction easy and interesting. Existing artificial intelligence methods show poor performance while giving most appropriate response to the user’s query. Hence at present rule-based Chatbot systems are more popular among the industries. In this paper, we present detailed study on implementing rule-based Chatbot systems. The paper discusses performance measurement parameters for Chatbot systems. The paper presents comparison between Google Dialogflow and IBM Watson, which are two most popular rule-based Chatbot implementation frameworks. The paper ends by listing expectations from future Chatbot systems.