# Neural Models for Reasoning over Multiple Mentions using Coreference

arXiv: https://arxiv.org/abs/1804.05922 · HTML: https://mlsanity.com/paper/1804.05922/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2018.

## Built on by (most cited first, 27 of 27)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction](https://mlsanity.com/paper/2102.10249/) (2021)
- [Word-Level Coreference Resolution](https://mlsanity.com/paper/2109.04127/) (2021)
- [Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable](https://mlsanity.com/paper/2110.13472/) (2021)
- [SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01709/) (2021)
- [On Generalization in Coreference Resolution](https://mlsanity.com/paper/2109.09667/) (2021)
- [WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia](https://mlsanity.com/paper/2104.05022/) (2021)
- [Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends](https://mlsanity.com/paper/2407.21489/) (2024)
- [Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference](https://mlsanity.com/paper/2110.05362/) (2021)
- [SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts](https://mlsanity.com/paper/2104.08809/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Cross-document Event Coreference Search: Task, Dataset and Modeling](https://mlsanity.com/paper/2210.12654/) (2022)
- [Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities](https://mlsanity.com/paper/2205.11438/) (2022)
- [Lexical Generalization Improves with Larger Models and Longer Training](https://mlsanity.com/paper/2210.12673/) (2022)
- [Major Entity Identification: A Generalizable Alternative to Coreference Resolution](https://mlsanity.com/paper/2406.14654/) (2024)
- [Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering](https://mlsanity.com/paper/2208.10297/) (2022)
- [Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering](https://mlsanity.com/paper/2102.03741/) (2021)
- [Interactive Machine Comprehension with Dynamic Knowledge Graphs](https://mlsanity.com/paper/2109.00077/) (2021)
- [Ask to Understand: Question Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2203.09073/) (2022)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)
- [ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehension](https://mlsanity.com/paper/2107.00841/) (2021)
- [Graph Attention with Hierarchies for Multi-hop Question Answering](https://mlsanity.com/paper/2301.11792/) (2023)
- [Ensemble Transfer Learning for Multilingual Coreference Resolution](https://mlsanity.com/paper/2301.09175/) (2023)
- [Perturbation-based Active Learning for Question Answering](https://mlsanity.com/paper/2311.02345/) (2023)
- [Benchmarking Gaslighting Attacks Against Speech Large Language Models](https://mlsanity.com/paper/2509.19858/) (2025)
- [Learning Complementary Action Modeling from Automotive Maintenance Instructions](https://mlsanity.com/paper/2606.27808/) (2026)

## Abstract (arXiv)

Many problems in NLP require aggregating information from multiple mentions of the same entity which may be far apart in the text. Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not suited to such tasks. We present a recurrent layer which is instead biased towards coreferent dependencies. The layer uses coreference annotations extracted from an external system to connect entity mentions belonging to the same cluster. Incorporating this layer into a state-of-the-art reading comprehension model improves performance on three datasets -- Wikihop, LAMBADA and the bAbi AI tasks -- with large gains when training data is scarce.