mlsanityData to 7 Oct 2026

Graph Refinement for Coreference Resolution

arXiv 2203.16574 ↗First posted 30 Mar 2022cs.CL cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

The state-of-the-art models for coreference resolution are based on independent mention pair-wise decisions. We propose a modelling approach that learns coreference at the document-level and takes global decisions. For this purpose, we model coreference links in a graph structure where the nodes are tokens in the text, and the edges represent the relationship between them. Our model predicts the graph in a non-autoregressive manner, then iteratively refines it based on previous predictions, allowing global dependencies between decisions. The experimental results show improvements over various baselines, reinforcing the hypothesis that document-level information improves conference resolution.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

18 of 32 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2018Deep contextualized word representationscited by 2,285
  6. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  7. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  8. 2017End-to-end Neural Coreference Resolutioncited by 240
  9. 2018Higher-order Coreference Resolution with Coarse-to-fine Inferencecited by 150
  10. 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
  11. 2019Coreference Resolution as Query-based Span Predictioncited by 91
  12. 2016Improving Coreference Resolution by Learning Entity-Level Distributed Representationscited by 50
6 more
  1. 2020Revealing the Myth of Higher-Order Inference in Coreference Resolutioncited by 49
  2. 2020Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networkscited by 29
  3. 2016Learning Global Features for Coreference Resolutioncited by 20
  4. 2020Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinementcited by 20
  5. 2019Graph-to-Graph Transformer for Transition-based Dependency Parsingcited by 13
  6. 2019Partially-supervised Mention Detectioncited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 2; 2025: 1.

7 papers.

  1. 2023Transformers as Graph-to-Graph Modelscited by 5
  2. 2025RAKG:Document-level Retrieval Augmented Knowledge Graph Constructioncited by 4
  3. 2022A hybrid entity-centric approach to Persian pronoun resolutioncited by 2
  4. 2024Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigmcited by 2
  5. 2023GADePo: Graph-Assisted Declarative Pooling Transformers for Document-Level Relation Extractioncited by 1
  6. 2022Review of coreference resolution in English and Persiancited by 0
  7. 2024Fast-and-Frugal Text-Graph Transformers are Effective Link Predictorscited by 0