Ensemble Transfer Learning for Multilingual Coreference Resolution

Tuan Lai, Heng Ji

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Entity coreference resolution is an important research problem with many applications, including information extraction and question answering. Coreference resolution for English has been studied extensively. However, there is relatively little work for other languages. A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. To overcome this challenge, we design a simple but effective ensemble-based framework that combines various transfer learning (TL) techniques. We first train several models using different TL methods. Then, during inference, we compute the unweighted average scores of the models’ predictions to extract the final set of predicted clusters. Furthermore, we also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts. Leveraging the idea that the coreferential links naturally exist between anchor texts pointing to the same article, our method builds a size-able distantly-supervised dataset for the target language that consists of tens of thousands of documents. We can pre-train a model on the pseudo-labeled dataset before finetuning it on the final target dataset. Experimental results on two benchmark datasets, OntoNotes and SemEval, confirm the effectiveness of our methods. Our best ensembles consistently outperform the baseline approach of simple training by up to 7.68% in the F1 score.

Original languageEnglish (US)
Title of host publication4th Workshop on Computational Approaches to Discourse, CODI 2023 - Proceedings of the Workshop
EditorsChloe Braud, Christian Hardmeier, Junyi Jessy Li, Sharid Loaiciga, Michael Strube, Amir Zeldes
PublisherAssociation for Computational Linguistics (ACL)
Number of pages13
ISBN (Electronic)9781959429890
StatePublished - 2023
Externally publishedYes
Event4th Workshop on Computational Approaches to Discourse, CODI 2023 - Toronto, Canada
Duration: Jul 13 2023Jul 14 2023

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X


Conference4th Workshop on Computational Approaches to Discourse, CODI 2023

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics


Dive into the research topics of 'Ensemble Transfer Learning for Multilingual Coreference Resolution'. Together they form a unique fingerprint.

Cite this