A Decision Model for Designing NLP Applications

Chen, Eason; Tseng, Yuen-Hsien

doi:10.1145/3487553.3524921

Cited by 11 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To let users compare, we will present five replies from five dialog agents with different character designs at once. Previous research indicated that a dialog system with multiple agents would bring a better chat experience because users can pay attention to the reply they like [4]. Nevertheless, another study [2] also stated that users would feel tiresome if multiple replies were similar.…”

Section: Dialog Agent and Chat Experiencementioning

confidence: 99%

Which Factors Predict the Chat Experience of a Natural Language Generation Dialogue Service?

Chen

2023

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

In this paper, we proposed a conceptual model to predict the chat experience in a natural language generation dialog system. We evaluated the model with 120 participants with Partial Least Squares Structural Equation Modeling (PLS-SEM) and obtained an R-square (𝑅 2 ) with 0.541. The model considers various factors, including the prompts used for generation; coherence, sentiment, and similarity in the conversation; and users' perceived dialog agents' favorability. We then further explore the effectiveness of the subset of our proposed model. The results showed that users' favorability and coherence, sentiment, and similarity in the dialogue are positive predictors of users' chat experience. Moreover, we found users may prefer dialog agents with characteristics of Extroversion, Openness, Conscientiousness, Agreeableness, and Non-Neuroticism. Through our research, an adaptive dialog system might use collected data to infer factors in our model, predict the chat experience for users through these factors, and optimize it by adjusting prompts. CCS CONCEPTS• Human-centered computing → User models; HCI theory, concepts and models; • Computing methodologies → Natural language generation; Discourse, dialogue and pragmatics.

show abstract

Section: Dialog Agent and Chat Experiencementioning

confidence: 99%

Which Factors Predict the Chat Experience of a Natural Language Generation Dialogue Service?

Chen

2023

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…ChatGPT avoids answering controversial topics. The chatbot does not express a personal opinion on any issues, does not race, does not profess religion, and does not answer the question about the purpose of its existence (Chen & Tseng, 2022). ChatGPT explains that it cannot think for itself.…”

Section: How the Model Differs From Other Text Neural Network?mentioning

confidence: 99%

“…ChatGPT has "memory". Unlike many neural network chatbots, ChatGPT remembers the details of the conversation and can build responses based on the information the user has already given (Chen & Tseng, 2022). For example, you can ask the chat what to give your mom for her birthday.…”

Section: How the Model Differs From Other Text Neural Network?mentioning

confidence: 99%

Voice Assistant Integrated with Chat GPT

Shafeeg¹,

Shazhaev²,

Mihaylov

et al. 2023

ijcs

View full text Add to dashboard Cite

AI has become deeply ingrained in the everyday life. The matter in question does not only touch upon the mobile phones that almost everyone carries within easy reach. Today, voice assistants and smart speakers are mainly used to turn on music, turn off the lights or forecast the weather. AI chatbots are getting smarter. The use of new technologies and the general development of neural networks makes it possible to chat or answer questions, write a script, a scientific work, or program code. One of the key differences from previous GPTs is that the new version is trained to continue the text and answer questions. The answers that the bot gives surprise users around the world. Yes, there are still questions about these answers and their validity, and everyone is sure that technology needs to be improved. For a technology to become revolutionary, it must find a better, new, breakthrough application. Although no, such an application has already been invented. Farcana decided to combine the functionality of the GPT chatbot and a voice assistant. By offering players a new approach to familiarizing themselves with game mechanics and general account management, Farcana promotes its advantages over others and rapidly contributes to AI's overall development in the digital society.

show abstract

“…Diagnosis. Diagnostic procedures and treatment process of disease have been the heart of healthcare for using artificial intelligence [41]. Previous expert system software in the past has demonstrated some potential to accurately enable human diagnose and treat disease.…”

Section: Important Of Artificial Intelligence and Natural Language Pr...mentioning

confidence: 99%

Analysis of Artificial Intelligence and Natural Language Processing Significance as Expert Systems Support for E-Health Using Pre-Train Deep Learning Models

Mah¹

2022

ATAIML

View full text Add to dashboard Cite

Artificial intelligence (AI) and natural language processing (NLP) are relentless technologies for healthcare that can support a strong and secure digital system with embedded applications of internet of things (IoTs). The study tried to build an artificial intelligence-natural language processing cluster system. In the system, rich content is extracted using parts of speech and then classified into an understandable dataset. The unavailable uniqueness systems with standardize process and procedures for artificial intelligence and natural language processing across different systems to support E-healthcare sector is a big challenge for nations and the world at large. Aim to train a cluster system that extract rich content and fit into a deep learning model frame to enable interpretation of the dataset for healthcare needs through a fast and secure digital system. The study uses (behavior-oriented driven and influential functions) to determine the significance of AI and NLP on E-health. Based on a selective scorings method, a rate of 1 out of 5 grading was developed called the Key Benefits score. The behavior-oriented drive and influential function allows an in-depth evaluation of E-health based on the selection of text content applied to the sample proposed study. Results show a score of 3.947 scale significance of NLP and AI on E-health. The study concluded that well-defined artificial intelligence and natural language processing applications are perfect areas that advance positive results in healthcare electronic services.

show abstract

A Decision Model for Designing NLP Applications

Cited by 11 publications

References 3 publications

Which Factors Predict the Chat Experience of a Natural Language Generation Dialogue Service?

Which Factors Predict the Chat Experience of a Natural Language Generation Dialogue Service?

Voice Assistant Integrated with Chat GPT

Analysis of Artificial Intelligence and Natural Language Processing Significance as Expert Systems Support for E-Health Using Pre-Train Deep Learning Models

Contact Info

Product

Resources

About