Word Sense Disambiguation with LSTM: Do We Really Need 100 Billion Words?

Recently, Yuan et al. (2016) have shown the effectiveness of using Long ShortTerm Memory (LSTM) for performing Word Sense Disambiguation (WSD). Their proposed technique outperformed the previous state-of-the-art with several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study of this technique using only openly available datasets (GigaWord, SemCore, OMSTI) and software (TensorFlow). From them, it emerged that stateof-the-art results can be obtained with much less data than hinted by Yuan et al. All code and trained models are made freely available.