KnowNER: Incremental Multilingual Knowledge in Named Entity Recognition
This work addresses the problem of improving NER accuracy for multiple languages by incrementally integrating external knowledge, offering a modular approach that can be adapted to various languages.
The authors tackled multilingual Named Entity Recognition by introducing KnowNER, a modular system that incorporates varying depths of external knowledge to train conditional random fields, achieving state-of-the-art performance across English, German, and Spanish.
KnowNER is a multilingual Named Entity Recognition (NER) system that leverages different degrees of external knowledge. A novel modular framework divides the knowledge into four categories according to the depth of knowledge they convey. Each category consists of a set of features automatically generated from different information sources (such as a knowledge-base, a list of names or document-specific semantic annotations) and is used to train a conditional random field (CRF). Since those information sources are usually multilingual, KnowNER can be easily trained for a wide range of languages. In this paper, we show that the incorporation of deeper knowledge systematically boosts accuracy and compare KnowNER with state-of-the-art NER approaches across three languages (i.e., English, German and Spanish) performing amongst state-of-the art systems in all of them.