Do LSTMs Learn Compositionally?
LSTM-based language models exhibit compositionality in their representations, but how this behavior emerges over the course of training has not been explored. Analyzing synthetic data experiments with contextual decomposition, we find that LSTMs learn long-range dependencies compositionally by building them from shorter constituents during training.
PDF AbstractTasks
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
No methods listed for this paper. Add
relevant methods here