Complementary to this explicit approach, noise can also be handled implicitly with the help of an auxiliary learning task.
However, this labeling tends to contain errors.
Multi-sense embeddings instead provide different vectors for each sense of a word.
If you still have questions or remarks, do not hesitate to us.
An analysis of the sense distributions and of the learned attention is provided as well.
Our analysis of word-sense ambiguity in the datasets can be used as a basis for future work.