Word sense disambiguation: a uinified evaluation framework and empirical comparison

Word Sense Disambiguation is a longstanding task in Natural Language Processing, lying at the core of human language understanding. However, the evaluation of automatic systems has been problematic, mainly due to the lack of a reliable evaluation framework. In this paper we develop a unified evaluation framework and analyze the performance of various Word Sense Disambiguation systems in a fair setup. The results show that supervised systems clearly outperform knowledge-based models. Among the supervised systems, a linear classi- fier trained on conventional local features still proves to be a hard baseline to beat. Nonetheless, recent approaches exploiting neural networks on unlabeled corpora achieve promising results, surpassing this hard baseline in most test sets.