Meet Turing by Borealis AI
Turing by Borealis AI is an interpretable text-to-SQL database interface that helps non-technical users to get insights from relational databases using natural language. Borealis AI has released a technical demo of Turing by Borealis AI to help translate natural language questions to SQL queries, unlocking the value of interacting with structured data without the need to write code.
Turing Features
-
SQL responses are explained in plain English to help with evaluating and understanding the results, which helps non-technical users select the appropriate SQL query from the highest-ranked options.
-
Trained on 100+ databases, it can generalize to new, never-seen-before databases to answer NLP questions.
-
Text-to-SQL framework is evaluated on the Spider benchmark, placing among the top performing frameworks with the record of the best performance in 2020 and much of 2020/21.
-
Equipped with a state-of-the-art cross-domain semantic parser (the core of the semantic parser has been released by the team). View related tutorials and research below.
Turing by Borealis AI Demo
View the Demo
Turing by Borealis AI is an accurate and interpretable natural language to SQL database interface that works on various domains.
Let’s watch it in action!
Anchored in
Research
Turing by Borealis AI has achieved and held state-of-the-art performance levels, while reducing accuracy issues thanks to its cross-domain text-to-SQL semantic parser. Typically, similar products have encountered serious accuracy and usability problems, making practical applications a challenge.
Turing by Borealis AI generates SQL and uses a synchronous context-free grammar system to provide a high-precision explanation, so that users can make sure the results are trustworthy and match the search intent. We have published several papers on the challenges we’ve encountered as part of our work.
-
TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
*P. Xu, *W. Zi, H. Shahidi, A. Kádár, K. Tang, W. Yang, J. Ateeq, H. Barot, M. Alon, and Y. Cao. Association for Computational Linguistics (ACL) & International Joint Conference on Natural Language Processing (IJCNLP), 2021
-
Optimizing Deeper Transformers on Small Datasets
Optimizing Deeper Transformers on Small Datasets
P. Xu, D. Kumar, W. Yang, W. Zi, K. Tang, C. Huang, J. Chi Kit Cheung, S. Prince, and Y. Cao. Association for Computational Linguistics (ACL) & International Joint Conference on Natural Language Processing (IJCNLP), 2021
-
Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data
Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data
S. Norouzi, K. Tang, and Y. Cao. Association for Computational Linguistics (ACL) & International Joint Conference on Natural Language Processing (IJCNLP), 2021
-
A Globally Normalized Neural Model for Semantic Parsing
A Globally Normalized Neural Model for Semantic Parsing
C. Huang, W. Yang, Y. Cao, O. R. Zaïane, and L. Mou. Association for Computational Linguistics & International Joint Conference on Natural Language Processing Workshop on Structured Prediction for NLP (ACL & IJCNLP), 2021