Multilingual Pre-trained Language Models in Cross-lingual NER Alignment for Zero-Shot Transfer

We propose a novel approach for cross-lingual Named Entity Recognition (NER) zero-shot transfer using parallel corpora. We built an entity alignment model on top of XLM-RoBERTa to project the entities detected on the English part of the parallel data to the target language sentences, whose accuracy surpasses all previous unsupervised models. With the alignment model we can get pseudo-labeled NER data set in the target language to train task-specific model. Unlike using translation methods, this approach benefits from natural fluency and nuances in target-language original corpus. We also propo

Research goal: What is the effect of incorporating multilingual pre-trained language models (e.g., XLM-RoBERTa, mBERT) as teachers in cross-lingual NER alignment methods on the F1 score performance for target languages with no labeled data?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.