Abstract
We study a new problem of cross-lingual transfer learning for event coreference resolution (ECR) where models trained on data from a source language are adapted for evaluations in different target languages. We introduce the first baseline model for this task based on XLM-RoBERTa, a state-of-the-art multilingual pre-trained language model. We also explore language adversarial neural networks (LANN) that present language discriminators to distinguish texts from the source and target languages to improve the language generalization for ECR. In addition, we introduce two novel mechanisms to further enhance the general representation learning of LANN, featuring: (i) multi-view alignment to penalize cross coreference-label alignment of examples in the source and target languages, and (ii) optimal transport to select close examples in the source and target languages to provide better training signals for the language discriminators. Finally, we perform extensive experiments for cross-lingual ECR from English to Spanish and Chinese to demonstrate the effectiveness of the proposed methods.
Highlights
Prior work on event coreference resolution (ECR) assumes the monolingual setting where training and test data are presented in the same languages
Current state-of-the-art ECR systems rely on large monolingual datasets to train advanced models (Nguyen et al, 2016; Choubey and Huang, 2018; Lu and Ng, 2017, 2018; Huang et al, 2019) that are only annotated for popular languages (e.g., English)
This paper explores cross-lingual transfer learning for ECR where models are trained on annotated documents in English and tested on documents from other languages
Summary
Prior work on ECR assumes the monolingual setting where training and test data are presented in the same languages. This paper explores cross-lingual transfer learning for ECR where models are trained on annotated documents in English (source language) and tested on documents from other languages (target languages).
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call