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 …
Recent progress in language model pre-training has achieved a great success via leveraging large-scale unstructured textual data. However, it is still a challenge to apply pre …
Transformers are widely used deep learning architectures. Existing transformers are mostly designed for sequences (texts or time series), images or videos, and graphs. This paper …
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 …
Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are …
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 …
The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables …
Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact …
T Zhang, X Yue, Y Li, H Sun - arXiv preprint arXiv:2311.09206, 2023 - arxiv.org
Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically interpret, augment, and query tables. Current methods often require …