search

amansrivastava17 / lstm-siamese-text-similarity

⚛️ It is keras based implementation of siamese architecture using lstm encoders to compute text similarity
MIT License
282 stars 88 forks source link

About Model Performance #8

Open zgzjdx opened 5 years ago

zgzjdx commented 5 years ago

Hi! Why i just got about 53% acc on dev set? What's the result you get on the dev set?

nishanthta commented 5 years ago

Try using this dataset (~10k examples) https://github.com/brmson/dataset-sts/tree/master/data/sts/sick2014

I was able to bump it to about 91% on this dev set using the same model. Just make sure to bump up the embedding dimension and the number of LSTM units accordingly