Support ELMo With Word Embedding

[huntzhan]

1. Dump the word embeddings from bilm-tf.
2. Load from weight file.

[huntzhan]

word ebd dump:

Saving variable lm/embedding:0 with name embedding
Saving variable lm/RNN_0/rnn/multi_rnn_cell/cell_0/lstm_cell/kernel:0 with name RNN_0/RNN/MultiRNNCell/Cell0/LSTMCell/W_0
Saving variable lm/RNN_0/rnn/multi_rnn_cell/cell_0/lstm_cell/bias:0 with name RNN_0/RNN/MultiRNNCell/Cell0/LSTMCell/B
Saving variable lm/RNN_0/rnn/multi_rnn_cell/cell_0/lstm_cell/projection/kernel:0 with name RNN_0/RNN/MultiRNNCell/Cell0/LSTMCell/W_P_0
Saving variable lm/RNN_0/rnn/multi_rnn_cell/cell_1/lstm_cell/kernel:0 with name RNN_0/RNN/MultiRNNCell/Cell1/LSTMCell/W_0
Saving variable lm/RNN_0/rnn/multi_rnn_cell/cell_1/lstm_cell/bias:0 with name RNN_0/RNN/MultiRNNCell/Cell1/LSTMCell/B
Saving variable lm/RNN_0/rnn/multi_rnn_cell/cell_1/lstm_cell/projection/kernel:0 with name RNN_0/RNN/MultiRNNCell/Cell1/LSTMCell/W_P_0
Saving variable lm/RNN_1/rnn/multi_rnn_cell/cell_0/lstm_cell/kernel:0 with name RNN_1/RNN/MultiRNNCell/Cell0/LSTMCell/W_0
Saving variable lm/RNN_1/rnn/multi_rnn_cell/cell_0/lstm_cell/bias:0 with name RNN_1/RNN/MultiRNNCell/Cell0/LSTMCell/B
Saving variable lm/RNN_1/rnn/multi_rnn_cell/cell_0/lstm_cell/projection/kernel:0 with name RNN_1/RNN/MultiRNNCell/Cell0/LSTMCell/W_P_0
Saving variable lm/RNN_1/rnn/multi_rnn_cell/cell_1/lstm_cell/kernel:0 with name RNN_1/RNN/MultiRNNCell/Cell1/LSTMCell/W_0
Saving variable lm/RNN_1/rnn/multi_rnn_cell/cell_1/lstm_cell/bias:0 with name RNN_1/RNN/MultiRNNCell/Cell1/LSTMCell/B
Saving variable lm/RNN_1/rnn/multi_rnn_cell/cell_1/lstm_cell/projection/kernel:0 with name RNN_1/RNN/MultiRNNCell/Cell1/LSTMCell/W_P_0

[huntzhan]

Decision:

• Manage a nn.Embedding instance in FastElmo.
• Provide a word2id utility function.
• Provide a CLI command to cache & dump Char CNN representation. (#3 is required)
• Provide a configuration snippet for AllenNLP Vocabulary. Use another repo to do this.