# Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference

arXiv: https://arxiv.org/abs/2110.05362 · HTML: https://mlsanity.com/paper/2110.05362/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 11 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Learning Dense Representations for Entity Retrieval](https://mlsanity.com/paper/1909.10506/) (2019)
- [Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution](https://mlsanity.com/paper/1906.01753/) (2019)
- [Multi-hop Question Answering via Reasoning Chains](https://mlsanity.com/paper/1910.02610/) (2019)
- [Neural Models for Reasoning over Multiple Mentions using Coreference](https://mlsanity.com/paper/1804.05922/) (2018)
- [Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization](https://mlsanity.com/paper/1805.10985/) (2018)
- [Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events](https://mlsanity.com/paper/1707.07344/) (2017)
- [CDLM: Cross-Document Language Modeling](https://mlsanity.com/paper/2101.00406/) (2021)
- [Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling](https://mlsanity.com/paper/2009.11032/) (2020)
- [Paraphrasing vs Coreferring: Two Sides of the Same Coin](https://mlsanity.com/paper/2004.14979/) (2020)
- [A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution](https://mlsanity.com/paper/1504.05929/) (2015)
- [CD2CR: Co-reference Resolution Across Documents and Domains](https://mlsanity.com/paper/2101.12637/) (2021)
- [Identity and Granularity of Events in Text](https://mlsanity.com/paper/1704.04259/) (2017)

## Built on by (most cited first, 16 of 16)

- [2 * n is better than n2: Decomposing Event Coreference Resolution into Two Tractable Problems](https://mlsanity.com/paper/2305.05672/) (2023)
- [Cross-document Event Coreference Search: Task, Dataset and Modeling](https://mlsanity.com/paper/2210.12654/) (2022)
- [What happens before and after: Multi-Event Commonsense in Event Coreference Resolution](https://mlsanity.com/paper/2302.09715/) (2023)
- [Linear Cross-document Event Coreference Resolution with X-AMR](https://mlsanity.com/paper/2404.08656/) (2024)
- [Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric Paraphrasing](https://mlsanity.com/paper/2407.11988/) (2024)
- [Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues](https://mlsanity.com/paper/2410.19301/) (2024)
- [A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution](https://mlsanity.com/paper/2404.01921/) (2024)
- [Multimodal Cross-Document Event Coreference Resolution Using Linear Semantic Transfer and Mixed-Modality Ensembles](https://mlsanity.com/paper/2404.08949/) (2024)
- [Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information](https://mlsanity.com/paper/2406.15990/) (2024)
- [Identifying and Investigating Global News Coverage of Critical Events Such as Disasters and Terrorist Attacks](https://mlsanity.com/paper/2506.12925/) (2025)
- [Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models](https://mlsanity.com/paper/2406.02148/) (2024)
- [Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation](https://mlsanity.com/paper/2404.03196/) (2024)
- [Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm](https://mlsanity.com/paper/2406.16021/) (2024)
- [EasyECR: A Library for Easy Implementation and Evaluation of Event Coreference Resolution Models](https://mlsanity.com/paper/2406.14106/) (2024)
- [Argument-Centric Causal Intervention Method for Mitigating Bias in Cross-Document Event Coreference Resolution](https://mlsanity.com/paper/2506.01488/) (2025)
- [Piecing Together Cross-Document Coreference Resolution Datasets: Systematic Dataset Analysis and Unification](https://mlsanity.com/paper/2603.00621/) (2026)

## Abstract (arXiv)

Performing event and entity coreference resolution across documents vastly increases the number of candidate mentions, making it intractable to do the full n2 pairwise comparisons. Existing approaches simplify by considering coreference only within document clusters, but this fails to handle inter-cluster coreference, common in many applications. As a result cross-document coreference algorithms are rarely applied to downstream tasks. We draw on an insight from discourse coherence theory: potential coreferences are constrained by the reader's discourse focus. We model the entities/events in a reader's focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters. We then use these neighborhoods to sample only hard negatives to train a fine-grained classifier on mention pairs and their local discourse features. Our approach achieves state-of-the-art results for both events and entities on the ECB+, Gun Violence, Football Coreference, and Cross-Domain Cross-Document Coreference corpora. Furthermore, training on multiple corpora improves average performance across all datasets by 17.2 F1 points, leading to a robust coreference resolution model for use in downstream tasks where link distribution is unknown.