# Information Extraction from Documents: Question Answering vs Token Classification in real-world setups

arXiv: https://arxiv.org/abs/2304.10994 · HTML: https://mlsanity.com/paper/2304.10994/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 21 Apr 2023.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [A Unified MRC Framework for Named Entity Recognition](https://mlsanity.com/paper/1910.11476/) (2019)
- [Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts](https://mlsanity.com/paper/2105.05796/) (2021)
- [A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets](https://mlsanity.com/paper/2006.11880/) (2020)
- [Learning from Noisy Labels for Entity-Centric Information Extraction](https://mlsanity.com/paper/2104.08656/) (2021)
- [Coarse-to-Fine Pre-training for Named Entity Recognition](https://mlsanity.com/paper/2010.08210/) (2020)
- [Detecting Label Errors in Token Classification Data](https://mlsanity.com/paper/2210.03920/) (2022)
- [Revising FUNSD dataset for key-value detection in document images](https://mlsanity.com/paper/2010.05322/) (2020)
- [NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading Comprehension](https://mlsanity.com/paper/2205.05904/) (2022)
- [Position Masking for Improved Layout-Aware Document Understanding](https://mlsanity.com/paper/2109.00442/) (2021)
- [Information Extraction from Visually Rich Documents with Font Style Embeddings](https://mlsanity.com/paper/2111.04045/) (2021)

## Abstract (arXiv)

Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision helped building document-focused pre-training methods, leveraging a multimodal understanding of the document text, layout and image modalities. However, these breakthroughs also led to the emergence of a new DocKIE subtask of extractive document Question Answering (DocQA), as part of the Machine Reading Comprehension (MRC) research field. In this work, we compare the Question Answering approach with the classical token classification approach for document key information extraction. We designed experiments to benchmark five different experimental setups : raw performances, robustness to noisy environment, capacity to extract long entities, fine-tuning speed on Few-Shot Learning and finally Zero-Shot Learning. Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach, while the QA approach could be a good alternative for noisy environment or long entities use-cases.