A survey on text-to-sql parsing: Concepts, methods, and future directions

B Qin, B Hui, L Wang, M Yang, J Li, B Li… - arXiv preprint arXiv …, 2022 - arxiv.org
Text-to-SQL parsing is an essential and challenging task. The goal of text-to-SQL parsing is
to convert a natural language (NL) question to its corresponding structured query language …

Table pre-training: A survey on model architectures, pre-training objectives, and downstream tasks

H Dong, Z Cheng, X He, M Zhou, A Zhou… - arXiv preprint arXiv …, 2022 - arxiv.org
Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs,
and various other document types, a flurry of table pre-training frameworks have been …

Harnessing the power of llms in practice: A survey on chatgpt and beyond

J Yang, H Jin, R Tang, X Han, Q Feng, H Jiang… - ACM Transactions on …, 2024 - dl.acm.org
This article presents a comprehensive and practical guide for practitioners and end-users
working with Large Language Models (LLMs) in their downstream Natural Language …

Transtab: Learning transferable tabular transformers across tables

Z Wang, J Sun - Advances in Neural Information Processing …, 2022 - proceedings.neurips.cc
Tabular data (or tables) are the most widely used data format in machine learning (ML).
However, ML models often assume the table structure keeps fixed in training and testing …

Shortcut learning of large language models in natural language understanding

M Du, F He, N Zou, D Tao, X Hu - Communications of the ACM, 2023 - dl.acm.org
Shortcut Learning of Large Language Models in Natural Language Understanding Page 1 110
COMMUNICATIONS OF THE ACM | JANUARY 2024 | VOL. 67 | NO. 1 research IMA GE B Y …

MultiHiertt: Numerical reasoning over multi hierarchical tabular and textual data

Y Zhao, Y Li, C Li, R Zhang - arXiv preprint arXiv:2206.01347, 2022 - arxiv.org
Numerical reasoning over hybrid data containing both textual and tabular content (eg,
financial reports) has recently attracted much attention in the NLP community. However …

Large language models are versatile decomposers: Decomposing evidence and questions for table-based reasoning

Y Ye, B Hui, M Yang, B Li, F Huang, Y Li - Proceedings of the 46th …, 2023 - dl.acm.org
Table-based reasoning has shown remarkable progress in a wide range of table-based
tasks. It is a challenging task, which requires reasoning over both free-form natural language …

Transformers for tabular data representation: A survey of models and applications

G Badaro, M Saeed, P Papotti - Transactions of the Association for …, 2023 - direct.mit.edu
In the last few years, the natural language processing community has witnessed advances
in neural representations of free texts with transformer-based language models (LMs). Given …

HYTREL: Hypergraph-enhanced tabular data representation learning

P Chen, S Sarkar, L Lausen… - Advances in …, 2024 - proceedings.neurips.cc
Abstract Language models pretrained on large collections of tabular data have
demonstrated their effectiveness in several downstream tasks. However, many of these …

SEQZERO: Few-shot compositional semantic parsing with sequential prompts and zero-shot models

J Yang, H Jiang, Q Yin, D Zhang, B Yin… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent research showed promising results on combining pretrained language models (LMs)
with canonical utterance for few-shot semantic parsing. The canonical utterance is often …