mlsanityData to 7 Oct 2026

Multilingual Coreference Resolution with Harmonized Annotations

arXiv 2107.12088 ↗First posted 26 Jul 2021cs.CLcited by 13

Not on the map. Why?

Abstract (arXiv)

In this paper, we present coreference resolution experiments with a newly created multilingual corpus CorefUD. We focus on the following languages: Czech, Russian, Polish, German, Spanish, and Catalan. In addition to monolingual experiments, we combine the training data in multilingual experiments and train two joined models -- for Slavic languages and for all the languages together. We rely on an end-to-end deep learning model that we slightly adapted for the CorefUD corpus. Our results show that we can profit from harmonized annotations, and using joined models helps significantly for the languages with smaller training data.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 7 of its 18 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

7 of 18 references.

References · 7

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  3. 2017End-to-end Neural Coreference Resolutioncited by 240
  4. 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
  5. 2020Revealing the Myth of Higher-Order Inference in Coreference Resolutioncited by 49
  6. 2018Anaphora and Coreference Resolution: A Reviewcited by 31
  7. 2018Neural Cross-Lingual Coreference Resolution and its Application to Entity Linkingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 2; 2025: 2; 2026: 3.

13 papers.

Sort:

  1. 2022Findings of the Shared Task on Multilingual Coreference Resolutioncited by 13
  2. 2022'UFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolutioncited by 8
  3. 2024CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Textcited by 6
  4. 2025Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?cited by 5
  5. 2022End-to-end Multilingual Coreference Resolution with Mention Head Predictioncited by 4
  6. 2024Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUDcited by 3
  7. 2025CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolutioncited by 2
  8. 2026Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entitiescited by 1
  9. 2023Ensemble Transfer Learning for Multilingual Coreference Resolutioncited by 0
  10. 2023SMDDH: Singleton Mention detection using Deep Learning in Hindi Textcited by 0
  11. 2023Investigating Multilingual Coreference Resolution by Universal Annotationscited by 0
  12. 2026Just Use XML: Revisiting Joint Translation and Label Projectioncited by 0
1 more
  1. 2026CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolutioncited by 0