In this paper, we investigate the utility of unsupervised lexical acquisition techniques to improve the quality of Named Entity Recognition and Classification (NERC) for the resource poor languages. As it is not a priori clear which unsupervised lexical acquisition techniques are useful for a particular task or language, careful feature selection is necessary. We treat feature selection as a multiobjective optimization (MOO) problem, and develop a suitable framework that fits well with the unsupervised lexical acquisition. Our experiments show performance improvements for two unsupervised features across three languages.
展开▼
