Sources of Transfer in Multilingual Named Entity Recognition
This addresses the challenge of limited annotations in multilingual NER for NLP applications, but it is incremental as it builds on existing fine-tuning methods.
The paper tackles the problem of polyglot named-entity recognition (NER) models underperforming monolingual ones despite more training data, finding that fine-tuning polyglot models on monolingual data consistently and significantly outperforms monolingual counterparts.
Named-entities are inherently multilingual, and annotations in any given language may be limited. This motivates us to consider polyglot named-entity recognition (NER), where one model is trained using annotated data drawn from more than one language. However, a straightforward implementation of this simple idea does not always work in practice: naive training of NER models using annotated data drawn from multiple languages consistently underperforms models trained on monolingual data alone, despite having access to more training data. The starting point of this paper is a simple solution to this problem, in which polyglot models are fine-tuned on monolingual data to consistently and significantly outperform their monolingual counterparts. To explain this phenomena, we explore the sources of multilingual transfer in polyglot NER models and examine the weight structure of polyglot models compared to their monolingual counterparts. We find that polyglot models efficiently share many parameters across languages and that fine-tuning may utilize a large number of those parameters.