A survey on deep learning approaches for text-to-SQL

Katsogiannis-Meimarakis, George; Koutrika, Georgia

doi:10.1007/s00778-022-00776-8

Cited by 29 publications

(9 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the former has a form-based interface, and although the latter is chatbot-based, it lacks chatbot qualities such as conversational feedback and viewing conversation history. In this context, some recent approaches attempted to split NLI high-level intents directly into nested SQL-queries [105,106].…”

Section: Discussionmentioning

confidence: 99%

Chatbot-Based Natural Language Interfaces for Data Visualisation: A Scoping Review

2023

View full text Add to dashboard Cite

Rapid growth in the generation of data from various sources has made data visualisation a valuable tool for analysing data. However, visual analysis can be a challenging task, not only due to intricate dashboards but also when dealing with complex and multidimensional data. In this context, advances in Natural Language Processing technologies have led to the development of Visualisation-oriented Natural Language Interfaces (V-NLIs). In this paper, we carry out a scoping review that analyses synergies between the fields of Data Visualisation and Natural Language Interaction. Specifically, we focus on chatbot-based V-NLI approaches and explore and discuss three research questions. The first two research questions focus on studying how chatbot-based V-NLIs contribute to interactions with the Data and Visual Spaces of the visualisation pipeline, while the third seeks to know how chatbot-based V-NLIs enhance users’ interaction with visualisations. Our findings show that the works in the literature put a strong focus on exploring tabular data with basic visualisations, with visual mapping primarily reliant on fixed layouts. Moreover, V-NLIs provide users with restricted guidance strategies, and few of them support high-level and follow-up queries. We identify challenges and possible research opportunities for the V-NLI community such as supporting high-level queries with complex data, integrating V-NLIs with more advanced systems such as Augmented Reality (AR) or Virtual Reality (VR), particularly for advanced visualisations, expanding guidance strategies beyond current limitations, adopting intelligent visual mapping techniques, and incorporating more sophisticated interaction methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Chatbot-Based Natural Language Interfaces for Data Visualisation: A Scoping Review

2023

View full text Add to dashboard Cite

show abstract

“…Currently, the platform provides two algorithms as natural language query interface services for researchers: namely, RAT-SQL and RYANSQL [27,28]. RAT-SQL encodes schema links and table structures based on Transformer by adding a relation-aware self-attention mechanism; Figure 5 illustrates the model structure of RAT-SQL.…”

Section: High Availability Of Human-computer Interactionmentioning

confidence: 99%

AI-Enabled Animal Behavior Analysis with High Usability: A Case Study on Open-Field Experiments

Chen,

Jiao,

Song

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In recent years, with the rapid development of medicine, pathology, toxicology, and neuroscience technology, animal behavior research has become essential in modern life science research. However, the current mainstream commercial animal behavior recognition tools only provide a single behavior recognition method, limiting the expansion of algorithms and how researchers interact with experimental data. To address this issue, we propose an AI-enabled, highly usable platform for analyzing experimental animal behavior, which aims to provide better flexibility, scalability, and interactivity to make the platform more usable. Researchers can flexibly select or extend different behavior recognition algorithms for automated recognition of animal behaviors or experience more convenient human-computer interaction through natural language descriptions only. A case study at a medical laboratory where the platform was used to evaluate behavioral differences between sick and healthy animals demonstrated the high usability of the platform.

show abstract

“…The transformative potential of generative AI models lies in revolutionising information discovery and consumption. While some have argued that the performance of generative AI models demonstrates that it might be the elusive "holy grail" of AI, many observe that the hype hides the obvious limitations inherent to them [14]. It is crucial to point out that the scope of what generative AI systems like ChatGPT can do is very limited.…”

Section: The Emerging Landscape Of Generative Aimentioning

confidence: 99%

Africa, ChatGPT, and Generative AI Systems: Ethical Benefits, Concerns, and the Need for Governance

Wakunuma,

Eke

2024

Philosophies

View full text Add to dashboard Cite

This paper examines the impact and implications of ChatGPT and other generative AI technologies within the African context while looking at the ethical benefits and concerns that are particularly pertinent to the continent. Through a robust analysis of ChatGPT and other generative AI systems using established approaches for analysing the ethics of emerging technologies, this paper provides unique ethical benefits and concerns for these systems in the African context. This analysis combined approaches such as anticipatory technology ethics (ATE), ethical impact assessment (EIA), and ethical issues of emerging ICT applications with AI (ETICA) with specific issues from the literature. The findings show that ChatGPT and other generative AI systems raise unique ethical concerns such as bias, intergenerational justice, exploitation of labour and cultural diversity in Africa but also have significant ethical benefits. These ethical concerns and benefits are considered crucial in shaping the design and deployment of ChatGPT and similar technologies responsibly. It further explores the potential applications of ChatGPT in critical domain areas such as education, agriculture, and healthcare, thereby demonstrating the transformative possibilities that these technologies can have on Africa. This paper underscores the critical role of AI governance as Africa increasingly adopts ChatGPT and similar AI systems. It argues that a comprehensive understanding of AI governance is essential not only for maximising the benefits of generative AI systems but also for facilitating a global dialogue. This dialogue aims to foster shared knowledge and insights between the Global North and the Global South, which is important for the development and creation of inclusive and equitable AI policies and practices that can be beneficial for all regions.

show abstract

A survey on deep learning approaches for text-to-SQL

Cited by 29 publications

References 78 publications

Chatbot-Based Natural Language Interfaces for Data Visualisation: A Scoping Review

Chatbot-Based Natural Language Interfaces for Data Visualisation: A Scoping Review

AI-Enabled Animal Behavior Analysis with High Usability: A Case Study on Open-Field Experiments

Africa, ChatGPT, and Generative AI Systems: Ethical Benefits, Concerns, and the Need for Governance

Contact Info

Product

Resources

About