# Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks

arXiv: https://arxiv.org/abs/2010.02807 · HTML: https://mlsanity.com/paper/2010.02807/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 29 of 29)

- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Entity Tracking in Language Models](https://mlsanity.com/paper/2305.02363/) (2023)
- [LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://mlsanity.com/paper/2205.12644/) (2022)
- [On Generalization in Coreference Resolution](https://mlsanity.com/paper/2109.09667/) (2021)
- [F-coref: Fast, Accurate and Easy to Use Coreference Resolution](https://mlsanity.com/paper/2209.04280/) (2022)
- [Moving on from OntoNotes: Coreference Resolution Model Transfer](https://mlsanity.com/paper/2104.08457/) (2021)
- [Sequential Cross-Document Coreference Resolution](https://mlsanity.com/paper/2104.08413/) (2021)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [Major Entity Identification: A Generalizable Alternative to Coreference Resolution](https://mlsanity.com/paper/2406.14654/) (2024)
- [Graph Refinement for Coreference Resolution](https://mlsanity.com/paper/2203.16574/) (2022)
- [Longtonotes: OntoNotes with Longer Coreference Chains](https://mlsanity.com/paper/2210.03650/) (2022)
- [The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works](https://mlsanity.com/paper/2510.15594/) (2025)
- [A Structured Span Selector](https://mlsanity.com/paper/2205.03977/) (2022)
- [DORE: Document Ordered Relation Extraction based on Generative Framework](https://mlsanity.com/paper/2210.16064/) (2022)
- [BOOKCOREF: Coreference Resolution at Book Scale](https://mlsanity.com/paper/2507.12075/) (2025)
- [Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations](https://mlsanity.com/paper/2205.10670/) (2022)
- [Multilingual Coreference Resolution in Multiparty Dialogue](https://mlsanity.com/paper/2208.01307/) (2022)
- [Sentence-Incremental Neural Coreference Resolution](https://mlsanity.com/paper/2305.16947/) (2023)
- [Parallel Data Helps Neural Entity Coreference Resolution](https://mlsanity.com/paper/2305.17709/) (2023)
- [Multilingual Coreference Resolution in Low-resource South Asian Languages](https://mlsanity.com/paper/2402.13571/) (2024)
- [Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities](https://mlsanity.com/paper/2605.21369/) (2026)
- [An analysis of full-size Russian complexly NER labelled corpus of Internet user reviews on the drugs based on deep learning and language neural nets](https://mlsanity.com/paper/2105.00059/) (2021)
- [CoreLM: Coreference-aware Language Model Fine-Tuning](https://mlsanity.com/paper/2111.02687/) (2021)
- [Review of coreference resolution in English and Persian](https://mlsanity.com/paper/2211.04428/) (2022)
- [What makes an entity salient in discourse?](https://mlsanity.com/paper/2508.16464/) (2025)
- [Mah=an=ama: A Unique Testbed for Literary Entity Discovery and Linking](https://mlsanity.com/paper/2509.19844/) (2025)
- [Efficient Seq2seq Coreference Resolution Using Entity Representations](https://mlsanity.com/paper/2510.14504/) (2025)
- [Learning What to Remember: Long-horizon Counterfactual Memory Optimization](https://mlsanity.com/paper/2609.37930/) (2026)

## Abstract (arXiv)

Long document coreference resolution remains a challenging task due to the large memory and runtime requirements of current models. Recent work doing incremental coreference resolution using just the global representation of entities shows practical benefits but requires keeping all entities in memory, which can be impractical for long documents. We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time, thus guaranteeing a linear runtime in length of document. We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy.