E5: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit and Extrapolate
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 1244-1258
Abstract
Zhehao Zhang, Yan Gao, Jian-Guang Lou. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.Keywords
This publication has 13 references indexed in Scilit:
- Large Language Models are Versatile Decomposers: Decomposing Evidence and Questions for Table-based Reasoning2023
- HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation2022
- GPT-NeoX-20B: An Open-Source Autoregressive Language Model2022
- TUTA2021
- HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data2020
- TaPas: Weakly Supervised Table Parsing via Pre-training2020
- Integrating spreadsheet data via accurate and low-effort extraction2014
- An automated approach for retrieving hierarchical data from HTML tables1999