1 code implementation • 26 Feb 2024 • Haoyang Li, Jing Zhang, Hanbing Liu, Ju Fan, Xiaokang Zhang, Jun Zhu, Renjie Wei, Hongyan Pan, Cuiping Li, Hong Chen
To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task.
1 code implementation • 7 Dec 2023 • Meihao Fan, Xiaoyue Han, Ju Fan, Chengliang Chai, Nan Tang, Guoliang Li, Xiaoyong Du
However, existing ICL approaches to ER typically necessitate providing a task description and a set of demonstrations for each entity pair and thus have limitations on the monetary cost of interfacing LLMs.
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 • 6 Jul 2023 • Nan Tang, Chenyu Yang, Ju Fan, Lei Cao, Yuyu Luo, Alon Halevy
We propose that verifying the outputs of generative AI from a data management perspective is an emerging issue for generative AI.
1 code implementation • 15 Jun 2023 • Zihui Gu, Ju Fan, Nan Tang, Songyue Zhang, Yuxin Zhang, Zui Chen, Lei Cao, Guoliang Li, Sam Madden, Xiaoyong Du
PLMs can perform well in schema alignment but struggle to achieve complex reasoning, while LLMs is superior in complex reasoning tasks but cannot achieve precise schema alignment.
1 code implementation • SIGMOD/PODS 2023 • Jianhong Tu, Ju Fan, Nan Tang, Peng Wang, Guoliang Li, Xiaoyong Du, Xiaofeng Jia, Song Gao
The widely used practice is to build task-specific or even dataset-specific solutions, which are hard to generalize and disable the opportunities of knowledge sharing that can be learned from different datasets and multiple tasks.
no code implementations • 7 Apr 2023 • Sibei Chen, Hanbing Liu, Weiting Jin, Xiangyu Sun, Xiaoyao Feng, Ju Fan, Xiaoyong Du, Nan Tang
Orchestrating a high-quality data preparation program is essential for successful machine learning (ML), but it is known to be time and effort consuming.
no code implementations • 26 Nov 2022 • Jianhong Tu, Zeyu Cui, Xiaohuan Zhou, Siqi Zheng, Kai Hu, Ju Fan, Chang Zhou
To achieve this task, we construct a synthetic dataset and develop an effective framework.
1 code implementation • 5 Nov 2022 • Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du
In particular, on the complex set of TabFact, which contains multiple operations, PASTA largely outperforms the previous state of the art by 4. 7 points (85. 6% vs. 80. 9%), and the gap between PASTA and human performance on the small TabFact test set is narrowed to just 1. 5 points (90. 6% vs. 92. 1%).
Ranked #2 on Table-based Fact Verification on TabFact
1 code implementation • SIGMOD/PODS 2022 • Jianhong Tu, Ju Fan, Nan Tang, Peng Wang, Chengliang Chai, Guoliang Li, Ruixue Fan, Xiaoyong Du
Entity resolution (ER) is a core problem of data integration.
Ranked #2 on Entity Resolution on WDC Watches-small
no code implementations • 4 Dec 2020 • Nan Tang, Ju Fan, Fangyi Li, Jianhong Tu, Xiaoyong Du, Guoliang Li, Sam Madden, Mourad Ouzzani
RPT is pre-trained for a tuple-to-tuple model by corrupting the input tuple and then learning a model to reconstruct the original tuple.
1 code implementation • 28 Aug 2020 • Ju Fan, Tongyu Liu, Guoliang Li, Junyou Chen, Yuwei Shen, Xiaoyong Du
We conduct extensive experiments to explore the design space and compare with traditional data synthesis approaches.
no code implementations • 13 Jun 2018 • Chengliang Chai, Ju Fan, Guoliang Li, Jiannan Wang, Yudian Zheng
Many data mining tasks cannot be completely addressed by auto- mated processes, such as sentiment analysis and image classification.