13 citations · 32 across the 8 of their papers we have counts for
10 papers
ReAcTable: Enhancing ReAct for Table Question Answering
Yunjia Zhang, Jordan Henkel, Avrilia Floratou +3
Table Question Answering (TQA) presents a substantial challenge at the intersection of natural language processing and data analytics. This task involves answering natural language…
Rapidash: Efficient Constraint Discovery via Rapid Verification
Zifan Liu, Shaleen Deep, Anna Fariha +3
Denial Constraint (DC) is a well-established formalism that captures a wide range of integrity constraints commonly encountered, including candidate keys, functional dependencies,…
From Words to Code: Harnessing Data for Program Synthesis from Natural Language
Anirudh Khatry, Joyce Cahoon, Jordan Henkel +9
Creating programs to correctly manipulate data is a difficult task, as the underlying programming languages and APIs can be challenging to learn for many users who are not skilled…
LST-Bench: Benchmarking Log-Structured Tables in the Cloud
Jesús Camacho-Rodríguez, Ashvin Agrawal, Anja Gruenheid +6
Data processing engines increasingly leverage distributed file systems for scalable, cost-effective storage. While the Apache Parquet columnar format has become a popular choice fo…
OneProvenance: Efficient Extraction of Dynamic Coarse-Grained Provenance from Database Logs [Technical Report]
Fotis Psallidas, Ashvin Agrawal, Chandru Sugunan +6
Provenance encodes information that connects datasets, their generation workflows, and associated metadata (e.g., who or when executed a query). As such, it is instrumental for a w…
Vamsa: Automated Provenance Tracking in Data Science Scripts
Mohammad Hossein Namaki, Avrilia Floratou, Fotis Psallidas +5
There has recently been a lot of ongoing research in the areas of fairness, bias and explainability of machine learning (ML) models due to the self-evident or regulatory requiremen…