Semi-supervised Word Sense Disambiguation with Neural Models
This work addresses a long-standing problem in natural language processing for improving text understanding, but it is incremental as it builds on existing neural methods.
The paper tackled word sense disambiguation by using an LSTM neural network to capture sequential and syntactic patterns, combined with semi-supervised label propagation to address data scarcity, achieving state-of-the-art results, particularly on verbs.
Determining the intended sense of words in text - word sense disambiguation (WSD) - is a long standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.