Showing papers on "Chatbot published in 2015"

Survey on Chatbot Design Techniques in Speech Conversation Systems

Abstract: Human-Computer Speech is gaining momentum as a technique of computer interaction. There has been a recent upsurge in speech based search engines and assistants such as Siri, Google Chrome and Cortana. Natural Language Processing (NLP) techniques such as NLTK for Python can be applied to analyse speech, and intelligent responses can be found by designing an engine to provide appropriate human like responses. This type of programme is called a Chatbot, which is the focus of this study. This paper presents a survey on the techniques used to design Chatbots and a comparison is made between different design techniques from nine carefully selected papers according to the main methods adopted. These papers are representative of the significant improvements in Chatbots in the last decade. The paper discusses the similarities and differences in the techniques and examines in particular the Loebner prize-winning Chatbots.

ALICE Chatbot: Trials and Outputs

Abstract: A chatbot is a conversational agent that interacts with users using natural language. Multi chatbots are available to serve in different domains. However, the knowledge base of chatbots is hand coded in its brain. This paper presents an overview of ALICE chatbot, its AIML format, and our experiments to generate different prototypes of ALICE automatically based on a corpus approach. A description of developed software which converts readable text (corpus) into AIML format is presented alongside with describing the different corpora we used. Our trials revealed the possibility of generating useful prototypes without the need for sophisticated natural language processing or complex machine learning techniques. These prototypes were used as tools to practice different languages, to visualize corpus, and to provide answers for questions.

Review of integrated applications with AIML based chatbot

Abstract: Artificial Intelligence Markup Language (AIML) is derived from Extensible Markup Language (XML) which is used to build up conversational agent (chatbot) artificially. There are developed a lot of works to make conversational agent. But low cost, configuration and availability make possible to use it in various applications. In this paper, we give a brief review of some applications which are used AIML chatbot for their conversational service. These applications are related to cultural heritage, e-learning, e-government, web base model, dialog model, semantic analysis framework, interaction framework, humorist expert, network management, adaptive modular architecture as well. In this case, they are not only providing useful services but also interact with customers and give solution of their problems through AIML chatbot instead of human beings. So, this is popular day by day with entrepreneur and users to provide efficient service.

Commercial Chatbot: Performance Evaluation, Usability Metrics and Quality Standards of Embodied Conversational Agents

Abstract: The aim of this paper is to explore commercial applications of chatbots, as well as to propose several measurement metrics to evaluate performance, usability and overall quality of an embodied conversational agent. On the basis of these metrics we examine existing Polish-speaking commercial chatbots that a) work in the B2C sector, b) reach the widest possible range of users, and c) are presumably the most advanced commercial deployments of their creators. We analyse various aspects of functioning of each embodied conversational agent: visual look, form of implementation on the website, speech synthesis unit, built-in knowledge base (with general and specialized information), presentation of knowledge and additional functionalities, conversational abilities and context sensitiveness, personality traits, personalization options, emergency responses in unexpected situations, possibility of rating chatbot and the website by the user. Our study reveals the current condition of Polish market of commercial virtual assistants and emphasizes the importance of a multidimensional evaluation of any commercial chatbot deployment.

Commercial Chatbot: Performance Evaluation, Usability Metrics and Quality Standards of Embodied Conversational Agents

Abstract: The aim of this paper is to explore commercial applications of chatbots, as well as to propose several measurement metrics to evaluate performance, usability and overall quality of an embodied conversational agent. On the basis of these metrics we examine existing Polish-speaking commercial chatbots that a) work in the B2C sector, b) reach the widest possible range of users, and c) are presumably the most advanced commercial deployments of their creators. We analyse various aspects of functioning of each embodied conversational agent: visual look, form of implementation on the website, speech synthesis unit, built-in knowledge base (with general and specialized information), presentation of knowledge and additional functionalities, conversational abilities and context sensitiveness, personality traits, personalization options, emergency responses in unexpected situations, possibility of rating chatbot and the website by the user. Our study reveals the current condition of Polish market of commercial virtual assistants and emphasizes the importance of a multidimensional evaluation of any commercial chatbot deployment.

Personalizing data system components and data sources as chatbots in a group chat session

Abstract: Provided are techniques for personalizing data system components and data sources as chatbots in a group chat session. A social media gateway interface with a chat adapter for a chat application is provided. One or more chatbots that each represent a corresponding component of a data system are created. The one or more chatbots and the chatbot adapter are used to manage each corresponding component of the data system.

Nombot: simplify food tracking

Abstract: Quantified self is a growing research area in human -- computer interaction. New techniques help users to track and optimize their daily activities. Some data is collected automatically. Others like information about nutrition have to be entered manually by the user. This process is labor -- intensive and quite often the motivation is fading over the time. In this paper, an approach is introduced to simplify food tracking. This developed procedure assimilates into daily routines. The instant messaging service called Telegram is used to propose the chatbot Nombot to the user. This bot communicates with the user and collects data about the nutrition of its chat partner. Different motivation types are considered. To evaluate the described implementation, an A/B study is conducted.

Design of chatbot with 3D avatar, voice interface, and facial expression

Abstract: A chatbot is a conventional agent that is able to interact with users in a given subject by using natural language. The conversations in most chatbot are still using a keyboard as the input. Keyboard input is considered ineffective as the conversation is not natural without any saying and a conversation is not just about words. Therefore, this paper propose a design of a chatbot with avatar and voice interaction to make a conversation more alive. This proposed approach method will come from using several API and using its output as another input to next API. It would take speech recognition to take input from user, then proceed it to chatbot API to receive the chatbot reply in a text form. The reply will be processed to text-to-speech recognition and created a spoken, audio version of the reply. Last, the computer will render an avatar whose gesture and lips are sync with the audio reply. This design would make every customer service or any service with human interaction can use it to make interaction more natural. This design can be further explored with additional tool such as web camera to make the agent can analyze the user's emotion and reaction.

Tical: Chatbot sobre o Atlas Linguístico do Brasil no WhatsApp

Abstract: Talking through mobile apps has become common nowadays and something essential and the WhatsApp is one of this App that stands out with thousands of users. It has such a great popularity that even some teachers use it as an extracurricular teaching methodology. Therefore, considering this accessibility advantage, a chatbot was developed to disseminate the Brazilian Linguistic Atlas, adding to the project, interdisciplinary features in Linguistics and Computer Science area, with its main focus on Natural Language Processing. The idea with this chatbot, in addition to show the Brazilian Atlas, is to stimulate other researchers desire to develop other subjects that are related to education using the WhatsApp, which is a common tool among young people.

Dialogue-based CALL: an overview of existing research

Abstract: Dialogue-based Computer-Assisted Language Learning (CALL) covers applications and systems allowing a learner to practice the target language in a meaning-focused conversational activity with an automated agent. We first present a common definition for dialogue-based CALL, based on three features: dialogue as the activity unit, computer as the interlocutor and negotiation of outcome through open learner production. We then report on a systematic literature review we conducted on the main scientific databases which, after filtering, resulted in 138 relevant papers which were analyzed and coded. Results show a scattered research field, with four different disciplinary approaches. We conclude with observations regarding the remaining challenges and opportunities for Intelligent CALL (ICALL) research.

CleverNAO: The intelligent conversational humanoid robot

Abstract: The objective of this work was the creation of a robotic system that any person could talk to in the English language, in particular, pairing an artificial intelligence algorithm that processes natural language with a physical robot that could synthesize speech. The result, called CleverNAO, is a successful combination of a chatbot application named Cleverbot with the NAO robot doing the speech synthesis. An attempt to include speech recognition was also made, with mixed success.

Open-domain personalized dialog system using user-interested topics in system responses

Abstract: We built a personalized example-based dialog system that constructs its responses by considering entities that the user has uttered, and topics in which the user has expressed interest. The system analyzes user input utterances, then uses DBpedia and Freebase to extract relevant entities and topics. The extracted entities and topics are stored in personal knowledge memory and are used when the system selects responses from the example database and generates responses. We conducted a human experiment in which evaluators rated dialog systems based on subjective metrics. The proposed dialog system that uses topics that are of interest to the user achieved higher evaluation scores for both personalization and satisfaction than the baseline systems. These results demonstrate that the use of topics in the system response provides a sense that the system pays attention to the user's utterances; as a consequence the user has a satisfactory dialog experience.

An Ergonomics Evaluation to Chatbot Equipped with Knowledge-Rich Mind

Abstract: Nowadays, more and more chatbots can get acquainted with the world by equipping with knowledge-rich minds which connect to Internet. In this paper, we will first explore how to integrate more knowledge into chatbot and how to make chatbot be aware of what are going on in the world. On top of that, a series of evaluations were performed on the prototype system. Through the evaluations, we mainly want to validate the proposed method in the prototype system and how the abundant level of knowledge accumulation of a chatbot affects the interactions between the chatbot and the users from the user satisfaction aspect. Experiment shows that the proposed method not only broadens the knowledge boundary of chatbot, but also makes the talks between users and chatbot more coherent. In addition, it shows that the level of user satisfaction is proportional to the amount of fact knowledge.

Chatbot with common-sense database

Abstract: In 1950 Alan Turing introduced the famous “Turing test” which tests if a machine can be as intelligent as a human by testing if it can communicate with a person in a “human” way. Inspired by this t ...

Penggunaan Named Entity Recognition dan Artificial Intelligence Markup Language untuk Penerapan Chatbot Berbasis Teks

Abstract: Aplikasi chatbot dapat digunakan untuk membantu memberikan kebutuhan informasi pada sistem layanan operator service. Sistem chatbot yang digunakan adalah sistem chatbot yang berbasiskan pada teks. Pada penelitian ini, chatbot dibuat untuk memenuhi kebutuhan informasi di ITHB dengan menggunakan Named Entity Recognition (NER) dan Artificial Intelligence Markup Language (AIML). NER digunakan untuk membantu mengenali pola (kata kunci) kalimat dari bahasa sehari-hari manusia (Natural Language Processing). AIML digunakan untuk memberikan jawaban yang relevan dan sesuai dengan pola (kata kunci) kalimat yang telah ditemukan di dalam bahasa manusia. Selain itu, pada penelitian ini juga dilakukan beberapa optimasi seperti optimasi pada proses perhitungan Naive Bayes pada NER, proses spelling correction, dan proses pattern matching yang terbukti dapat mempercepat dan meningkatkan akurasi sistem chatbot dalam proses pencarian jawaban. Berdasarkan hasil pengujian, sistem chatbot ini dapat mengenali pola kalimat bahasa manusia dengan akurasi (NER) hingga 97% dan sistem dapat memberikan jawaban yang tepat dengan akurasi hingga 90% berdasarkan pola yang telah ditemukan tersebut. In operator service system area, information is an essential needs for every individuals. Chatbot application can be used to support the fulfilment of information in operation service system. Chatbot system that will be implemented is a text-based chatbot system. In this paper, chatbot was made in order to fulfil the information needs in ITHB by using Named Entity Recognition (NER) and Artificial Intelligence Markup Language (AIML). NER is used to recognize the sentence pattern (keyword) in human natural language (Natural Language Processing). AIML is used to process relevant responses based on the keyword patterns found in human natural language which then will be transformed into data which can be processed and understood by system. This research also covers several optimizations, such as Naive Bayes calculation optimization in NER, spelling correction optimization, and pattern matching optimization that has been proven to hasten and increase chatbot system’s accuracy in finding answers as response. Based on the empirical examination, this chatbot system can recognize human sentence pattern (NER process) with accuracy of 97% and system can provide suitable response with accuracy of 90% based on the recognized patterns from NER process.

Towards an efficient voice-based chatbot

Abstract: In this paper we present the development and integration of technologies used in an experimental natural conversation system designed to run on a humanoid robot (NAO H-25), its design and the concepts on which it's based. In addition, we perform a brief analysis of its operation with information collected through human trials conducted heuristically, in the areas of performance and efficiency as well as accuracy and consistency of the system's output.

An Educational Talking Toy based on an Enhanced Chatbot

Abstract: Children are often motivated in their communication behaviour by pets or toys. Our aim is to investigate, how communication with “intelligent“ systems affects interaction of children. Enhanced chatbot technology – hidden in toys - is used to talk to children. In the Hablame-project (started as part of the EU-funded Gaviota project) a first prototype talking German is available. We outline the technical solution, and discuss further steps.

Adopting Semantic Similarity for Utterance Candidates Discovery from Human-to-Human Dialogue Corpus

Abstract: Having appropriate utterances in response to user input is an essential element to sustain the flow of conversation in dialogue systems, and a basic and fundamental element for maintaining such conversation coherence is an adjacency pair. To find appropriate candidates for adjacency pairs completion, and thus contribute to avoiding conversational disrupt in casual chatbot systems, we suggest an approach that utilizes human-to-human chat logs, and combines standard Information Retrieval methods and semantic similarity measures based on distributed word representations. The experimental results show the approach improves the quality of utterance pairs compared to standard IR-based methods.