An Overview of Chatbot Technology

Adamopoulou, Eleni; Moussiades, Lefteris

doi:10.1007/978-3-030-49186-4_31

Cited by 483 publications

(328 citation statements)

References 26 publications

Supporting

Mentioning

201

Contrasting

Unclassified

Order By: Relevance

“…RiveScript or Artificial Intelligence Scripting Language is an implementation of a line-based scripting language [15]. RiveScript is open-source software with an interface for many programming languages such as Python, Java, or JavaScript.…”

Section: Rivescriptmentioning

confidence: 99%

Developing Medical Virtual Teaching Assistant Based on Speech Recognition Technology

et al. 2021

View full text Add to dashboard Cite

This paper proposes to present the results of the development of the Virtual Teaching Assistant (VTA). This system is an e-learning module as a learning aid for medical students currently pursuing professional medical doctor in hospitals. In Indonesia, students of the medical doctor profession education must study and work in hospitals like an experienced doctor. They interact directly with patients and provide the same services as doctors. Every student has a professional doctor at the hospital as a mentor or companion. However, student meetings with accompanying doctors are minimal. It is not uncommon for students to encounter difficulties when dealing with patients, but they do not immediately receive guidance. As students, it is natural that they sometimes forget the theory. These students need a theoretical learning source that is fast and practical, which students can use between activities. We developed VTA to meet the needs of information and fast learning resources. VTA can run on computer, laptop, or smartphones by utilizing speech recognition technology. Students only need to ask questions in the form of speech using their everyday language, and VTA will provide answers. Although the VTA answer is still not satisfactory, it potentially to support Question and Answer-based mobile learning for particularly learning subject.

show abstract

Section: Rivescriptmentioning

confidence: 99%

Developing Medical Virtual Teaching Assistant Based on Speech Recognition Technology

et al. 2021

View full text Add to dashboard Cite

show abstract

“…According to the Scopus paper analysis by [6], the rapid growth of interest in chatbots is especially visible after 2016, with a special focus on innovative DNN technology in recent years. The essence of this related work analysis is to highlight methodologies that could be the most effective for the intent detection task.…”

Section: Related Workmentioning

confidence: 99%

Monolingual and Cross-Lingual Intent Detection without Training Data in Target Languages

2021

View full text Add to dashboard Cite

Due to recent DNN advancements, many NLP problems can be effectively solved using transformer-based models and supervised data. Unfortunately, such data is not available in some languages. This research is based on assumptions that (1) training data can be obtained by the machine translating it from another language; (2) there are cross-lingual solutions that work without the training data in the target language. Consequently, in this research, we use the English dataset and solve the intent detection problem for five target languages (German, French, Lithuanian, Latvian, and Portuguese). When seeking the most accurate solutions, we investigate BERT-based word and sentence transformers together with eager learning classifiers (CNN, BERT fine-tuning, FFNN) and lazy learning approach (Cosine similarity as the memory-based method). We offer and evaluate several strategies to overcome the data scarcity problem with machine translation, cross-lingual models, and a combination of the previous two. The experimental investigation revealed the robustness of sentence transformers under various cross-lingual conditions. The accuracy equal to ~0.842 is achieved with the English dataset with completely monolingual models is considered our top-line. However, cross-lingual approaches demonstrate similar accuracy levels reaching ~0.831, ~0.829, ~0.853, ~0.831, and ~0.813 on German, French, Lithuanian, Latvian, and Portuguese languages.

show abstract

“…Segundo [Adamopoulou and Moussiades 2020], os principais requisitos para projetar um chatbot tradicional são: representação do conhecimento (i.e. um conjunto de dados sobre o domínio para o qual se deseja aplicar), uma estratégia de geração de respostas e um conjunto de respostas neutras predefinidas para responder quando a expressão do usuário nãoé entendida.…”

Section: Arquitetura Propostaunclassified

“…Neste trabalho, investigou-se, via revisão da literatura, algumas arquiteturas propostas para o projeto de chatbots com o intuito de modificá-las para acomodar aprendizagem ao longo da vida. Especificamente, a arquitetura geral apresentada em [Adamopoulou and Moussiades 2020] foi modificada para acomodar o paradigma de aprendizagem por reforço baseada em modelo. O que distingue este trabalho dos demais revisados na literaturaé a aplicação de RL baseda em modelo na qual o chatbot vai criar e manter um modelo do usuário no estilo daqueles utilizados em sistemas tutoriais inteligentes.…”

Section: Conclusãounclassified

Proposta de Arquitetura de Software para um Chatbot com aprendizagem

Soares¹,

Maia²

2020

Anais Da Escola Regional De Computação Ceará, Maranhão, Piauí (ERCEMAPI 2020)

View full text Add to dashboard Cite

Uma fraqueza dos agentes de conversação (chatbot) mais utilizados hoje é que eles não são projetados para aprender durante o processo de conversação. O seu conhecimento é fixado durante o projeto e eles não tiram vantagem da interação com os usuários para evoluir o seu conhecimento e a sua capacidade de diálogo. Neste trabalho, o projeto de um Chatbot com aprendizagem ao longo da vida é inserido no arcabouço de Aprendizagem por Reforço. Embora aprendizagem por reforço já tenha sido utilizada antes, a revisão da literatura apresentada mostra que essa proposta é inovadora.

show abstract

An Overview of Chatbot Technology

Cited by 483 publications

References 26 publications

Developing Medical Virtual Teaching Assistant Based on Speech Recognition Technology

Developing Medical Virtual Teaching Assistant Based on Speech Recognition Technology

Monolingual and Cross-Lingual Intent Detection without Training Data in Target Languages

Proposta de Arquitetura de Software para um Chatbot com aprendizagem

Contact Info

Product

Resources

About