Currently we combine unary constituents with the POS tag of the word. And we train an LSTM tagger using Dynet.
- Python 2.7
- Numpy
- DyNet
python tags.py data/10sentences.sample
This will produce a file data/10sentences.sample.supertags
python dynet_bilstm_tagger.py --train data/10sentences.sample.supertags --dev data/10sentences.sample.supertags --model model