Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking
This addresses cross-lingual NLP tasks like entity linking for multilingual applications, but it is incremental as it builds on existing multi-lingual embeddings and features.
The paper tackles cross-lingual coreference resolution by proposing a neural model using multi-lingual embeddings, achieving competitive results when trained on English and tested on Chinese and Spanish, and improving entity linking accuracy over a prior system without using annotated data in those languages.
We propose an entity-centric neural cross-lingual coreference model that builds on multi-lingual embeddings and language-independent features. We perform both intrinsic and extrinsic evaluations of our model. In the intrinsic evaluation, we show that our model, when trained on English and tested on Chinese and Spanish, achieves competitive results to the models trained directly on Chinese and Spanish respectively. In the extrinsic evaluation, we show that our English model helps achieve superior entity linking accuracy on Chinese and Spanish test sets than the top 2015 TAC system without using any annotated data from Chinese or Spanish.