Arabic Named Entity Recognition using Word Representations
This work addresses NER for Arabic, an incremental improvement applying known methods to a new language.
The study tackled the problem of Arabic Named Entity Recognition by investigating whether word representations could improve performance, finding that combining Brown clusters and word embedding features provided nearly a 10% F1-score improvement over the baseline.
Recent work has shown the effectiveness of the word representations features in significantly improving supervised NER for the English language. In this study we investigate whether word representations can also boost supervised NER in Arabic. We use word representations as additional features in a Conditional Random Field (CRF) model and we systematically compare three popular neural word embedding algorithms (SKIP-gram, CBOW and GloVe) and six different approaches for integrating word representations into NER system. Experimental results show that Brown Clustering achieves the best performance among the six approaches. Concerning the word embedding features, the clustering embedding features outperform other embedding features and the distributional prototypes produce the second best result. Moreover, the combination of Brown clusters and word embedding features provides additional improvement of nearly 10% in F1-score over the baseline.