Neural Cross-Lingual Transfer and Limited Annotated Data for Named Entity Recognition in Danish
This work addresses the scarcity of annotated data for Danish NER, which is an incremental improvement for a specific language domain.
The paper tackled the problem of Named Entity Recognition (NER) for Danish, which suffers from limited annotated data, by studying cross-lingual transfer and its combination with small amounts of gold data to evaluate and improve performance.
Named Entity Recognition (NER) has greatly advanced by the introduction of deep neural architectures. However, the success of these methods depends on large amounts of training data. The scarcity of publicly-available human-labeled datasets has resulted in limited evaluation of existing NER systems, as is the case for Danish. This paper studies the effectiveness of cross-lingual transfer for Danish, evaluates its complementarity to limited gold data, and sheds light on performance of Danish NER.