Experiments on Active Learning for Croatian Word Sense Disambiguation
Domagoj Alagić, Jan Šnajder · 2015
Supervised word sense disambiguation (WSD) has been shown to achieve state-ofthe-art results but at high annotation costs. Active learning can ameliorate that problem by allowing the model to dynamically choose the most informative word contexts for manual labeling. In this paper we investigate the use of active learning for Croatian WSD. We adopt a lexical sample approach and compile a corresponding senseannotated dataset on which we evaluate our models. We carry out a detailed investigation of the different active learning setups, and show that labeling as few as 100 instances suffices to reach near-optimal performance.