Semi-supervised Word Sense Disambiguation with Neural Models
arXiv:1603.07012
Abstract
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.
References in corpus (4)
Cited by in corpus (10)
- Towards better substitution-based word sense induction
- Using BERT for Word Sense Disambiguation
- LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond
- EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
- Exemplar Guided Active Learning
- A Novel Neural Sequence Model with Multiple Attentions for Word Sense Disambiguation
- Decomposing Word Embedding with the Capsule Network
- Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation
- Language models in word sense disambiguation for Polish
- A Short Survey on Sense-Annotated Corpora