no code implementations • 1 Oct 2023 • Zui Chen, Lei Cao, Sam Madden, Tim Kraska, Zeyuan Shang, Ju Fan, Nan Tang, Zihui Gu, Chunwei Liu, Michael Cafarella
SEED uses these generated modules to process most of the data records and dynamically decides when the LLM should step in to directly process some individual records, possibly using the data-access modules to retrieve relevant information from the data sources to assist the LLM in solving the task.
no code implementations • 24 Mar 2021 • Songtao He, Favyen Bastani, Mohammad Alizadeh, Hari Balakrishnan, Michael Cafarella, Tim Kraska, Sam Madden
We show TagMe can produce high-quality object annotations in a fully-automatic and low-cost way.
no code implementations • 2 Mar 2021 • El Kindi Rezig, Michael Cafarella, Vijay Gadepally
In this report, we highlight a number of tools that can be used to simplify data integration and preparation steps.
1 code implementation • 28 Apr 2020 • Alana Marzoev, Samuel Madden, M. Frans Kaashoek, Michael Cafarella, Jacob Andreas
Large, human-annotated datasets are central to the development of natural language processing models.
1 code implementation • 16 Mar 2020 • Christopher Baik, Zhongjun Jin, Michael Cafarella, H. V. Jagadish
We present results from user studies in which Duoquest demonstrates a 62. 5% absolute increase in query construction accuracy over a state-of-the-art NLI and comparable accuracy to a PBE system on a more limited workload supported by the PBE system.
Databases
no code implementations • 11 Jun 2018 • Michael R. Anderson, Michael Cafarella, German Ros, Thomas F. Wenisch
Modern extraction techniques are based on deep convolutional neural networks (CNNs) and can classify objects within images with astounding accuracy.
no code implementations • 16 Mar 2017 • Yongjoo Park, Ahmad Shahab Tajik, Michael Cafarella, Barzan Mozafari
Also, processing more queries should continuously enhance our knowledge of the underlying distribution, and hence lead to increasingly faster response times for future queries.