# Iterative Document-level Information Extraction via Imitation Learning

arXiv: https://arxiv.org/abs/2210.06600 · HTML: https://mlsanity.com/paper/2210.06600/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 59 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Levenshtein Transformer](https://mlsanity.com/paper/1905.11006/) (2019)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [Cross-Sentence N-ary Relation Extraction with Graph LSTMs](https://mlsanity.com/paper/1708.03743/) (2017)
- [Multi-Sentence Argument Linking](https://mlsanity.com/paper/1911.03766/) (2019)
- [Distant Supervision for Relation Extraction beyond the Sentence Boundary](https://mlsanity.com/paper/1609.04873/) (2016)
- [Learning to Search Better Than Your Teacher](https://mlsanity.com/paper/1502.02206/) (2015)
- [Document-level Entity-based Extraction as Template Generation](https://mlsanity.com/paper/2109.04901/) (2021)
- [LOME: Large Ontology Multilingual Extraction](https://mlsanity.com/paper/2101.12175/) (2021)
- [Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction](https://mlsanity.com/paper/2109.06798/) (2021)
- [A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification](https://mlsanity.com/paper/1807.04990/) (2018)
- [Improving Long Distance Slot Carryover in Spoken Dialogue Systems](https://mlsanity.com/paper/1906.01149/) (2019)

## Built on by (most cited first, 11 of 11)

- [A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers](https://mlsanity.com/paper/2306.02051/) (2023)
- [WikiVideo: Article Generation from Multiple Videos](https://mlsanity.com/paper/2504.00939/) (2025)
- [A Unified View of Evaluation Metrics for Structured Prediction](https://mlsanity.com/paper/2310.13793/) (2023)
- [Grounding Partially-Defined Events in Multimodal Data](https://mlsanity.com/paper/2410.05267/) (2024)
- [A Survey of Video Datasets for Grounded Event Understanding](https://mlsanity.com/paper/2406.09646/) (2024)
- [MultiMUC: Multilingual Template Filling on MUC-4](https://mlsanity.com/paper/2401.16209/) (2024)
- [On Event Individuation for Document-Level Information Extraction](https://mlsanity.com/paper/2212.09702/) (2022)
- [FAMuS: Frames Across Multiple Sources](https://mlsanity.com/paper/2311.05601/) (2023)
- [Event-Keyed Summarization](https://mlsanity.com/paper/2402.06973/) (2024)
- [Are Triggers Needed for Document-Level Event Extraction?](https://mlsanity.com/paper/2411.08708/) (2024)
- [Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization](https://mlsanity.com/paper/2607.01972/) (2026)

## Abstract (arXiv)

We present a novel iterative extraction model, IterX, for extracting complex relations, or templates (i.e., N-tuples representing a mapping from named slots to spans of text) within a document. Documents may feature zero or more instances of a template of any given type, and the task of template extraction entails identifying the templates in a document and extracting each template's slot values. Our imitation learning approach casts the problem as a Markov decision process (MDP), and relieves the need to use predefined template orders to train an extractor. It leads to state-of-the-art results on two established benchmarks -- 4-ary relation extraction on SciREX and template extraction on MUC-4 -- as well as a strong baseline on the new BETTER Granular task.