Design of a Chatbot for People Under Distress using Transformer Model

Konapur, Sushruth P; Krishna, Tejas; Varun, G; Uma, R.; Sarojadevi, H.

doi:10.1109/gcat52182.2021.9587796

Cited by 4 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generative models require extensive and diverse datasets, which can be resource-intensive to acquire and maintain [22].On the other hand, retrieval-based models rely on relevant training data and these models are resource efficient. Additionally, efficiently predicting and integrating user emotions into response generation poses another critical challenge [22]. This involves accurately recognizing emotions from user inputs and providing contextually appropriate responses [25].…”

Section: Methodsmentioning

confidence: 99%

“…Generative-based models, while offering potential for creativity, often struggle with maintaining logical consistency. Generative models require extensive and diverse datasets, which can be resource-intensive to acquire and maintain [22].On the other hand, retrieval-based models rely on relevant training data and these models are resource efficient. Additionally, efficiently predicting and integrating user emotions into response generation poses another critical challenge [22].…”

Section: Methodsmentioning

confidence: 99%

“…While this approach enhances empathy in responses, limiting its ability to precisely capture and generate specific emotional responses. Additionally, these models demand very high computational resources for training and are heavily dependent on vast datasets [22].…”

Section: Related Workmentioning

confidence: 99%

“…The proposed system is designed by integrating insights from four previous studies. Clustering of emotions will be used to capture a larger range of emotions and to generalize more [22]. [22] and [27] will be used to cluster the emotions effectively based on Valence-Arousal-Dominance (VAD) intensity.…”

Section: Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Ashen

2024

Preprint

View full text Add to dashboard Cite

Chatbots are becoming increasingly prevalent in our daily lives, handling a variety of tasks from booking flights to checking the balance of a bank account. However, these interactions are often limited to transactional nature, lacking the depth and nuance of natural human conversations. Therefore, while chatbots are becoming more sophisticated, they still have a significant way to go in terms of authentic human-like interaction. Enhancing chatbots' ability to interact with humans and making them more user-friendly is a crucial challenge in contemporary conversational technology. One promising approach is to imbue these chatbots with the ability to express and understand emotions. Hence, the focus is on developing empathetic dialogue systems that effectively model empathy, ultimately making chatbots more human-like in their interactions with users. In this project, A retrieval-based approach is adopted to mitigate the limitations encountered in generative-based models, particularly concerning logical coherence and response appropriateness. Unlike generative models, retrieval-based approaches offer a more pragmatic solution that demands fewer computational resources. Through the integration of deep learning techniques, transparency in decision-making processes is ensured by eXplainable Artificial Intelligence (XAI), providing users with insights into the chatbot's reasoning. Furthermore, clustering techniques are leveraged to generalize various emotion types, allowing the chatbot to cater to a broader spectrum of emotional inputs effectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Ashen

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…(Global Marketing…, 2023). According to previous studies, chat bots, typically built on machine learning, are mainly used in areas such as customer support (Vu et al, 2021), therapy (Konapur et al, 2021) or personal devices (for example, the Siri bot in Apple products) (Mohamed et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Development of a Chat Bot Algorithm to Improve the Efficiency of the Process of Organizing Corporate Training

2024

European Journal of Contemporary Education

View full text Add to dashboard Cite

The development of professional competencies of personnel is an important task for modern organizations. And its effective solution is facilitated by the emerging opportunity to use artificial intelligence, with the help of which the boundaries of access to the latest tools and training technologies are expanding, allowing personnel to adapt to changes and prepare them to solve current problems and achieve strategic goals. Also, the use of digital services and tools opens up broad prospects for ensuring continuous training and development of personnel, which helps to increase the value of human capital in the organization. One of the promising innovations using artificial intelligence is chat bot technology, which provides quick information search, improves adaptation and communication processes, activates human potential, and helps improve learning efficiency through additional interaction with people through text messages. The article presents a summary of the experience of organizations in using chat bot practices in the HRM system. The implementation of the chat bot technology saves labor costs and allows companies' management to personalize training, provide staff with highly intelligent support, free up their time from performing routine tasks, maintain a high level of interactivity in the learning process, while continuously monitoring the acquisition of knowledge by employees with receiving feedback. The following methods were used for the study: analysis, synthesis, comparison, graphic description, structuring, modeling, visualization. The authors have developed algorithms for working with requests for personnel training. It has been shown that the implementation of chat bot technology saves labor costs and increases the efficiency of work with internal clients of the HR department. The authors calculated the effectiveness of the chat bot by reducing the time spent processing applications from internal clients of the HR department. In further research, it is

show abstract

ChatGPT: Its Applications and Limitations

Chowdhury,

Haque

2023

2023 3rd International Conference on Intelligent Technologies (CONIT)

View full text Add to dashboard Cite

Design of a Chatbot for People Under Distress using Transformer Model

Cited by 4 publications

References 11 publications

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Development of a Chat Bot Algorithm to Improve the Efficiency of the Process of Organizing Corporate Training

ChatGPT: Its Applications and Limitations

Contact Info

Product

Resources

About