Add more metrics for evaluating test runs

[shivankacker]

The following metrics for comparing responses would be best:

1. GLOVE + Cosine Similarity
2. BertScore: compute token similarity using contextual embeddings
3. Glove + Word2vec + BiLSTM : word embedding is first made with Glove and Word2Vec, two BLSTM networks are used separately for sentence embedding, these are passed through a classifier
4. Word mover Distance
5. Pretrained sentence encoders: Such as Google Sentence encoder
6. Siamese Manhattan LSTM

cc. @bodhish

[bodhish]

We will just implement 1/2 from the list; lets do some research on this before going ahead;