# From Dataset Recycling to Multi-Property Extraction and Beyond

arXiv: https://arxiv.org/abs/2011.03228 · HTML: https://mlsanity.com/paper/2011.03228/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer](https://mlsanity.com/paper/2102.09550/) (2021)
- [Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts](https://mlsanity.com/paper/2105.05796/) (2021)
- [STable: Table Generation Framework for Encoder-Decoder Models](https://mlsanity.com/paper/2206.04045/) (2022)
- [Notes on Applicability of GPT-4 to Document Understanding](https://mlsanity.com/paper/2405.18433/) (2024)
- [Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs](https://mlsanity.com/paper/2305.16344/) (2023)
- [Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset](https://mlsanity.com/paper/2412.20072/) (2024)

## Abstract (arXiv)

This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled-a newly developed public dataset and the task of multiple property extraction. It uses the same data as WikiReading but does not inherit its predecessor's identified disadvantages. In addition, we provide a human-annotated test set with diagnostic subsets for a detailed analysis of model performance.