Week 6- Book Summary Classifier
This week we aimed to make the CNN and Text classifications of our project. Along with that we tried to make a text generator too.
Here is how it works..
LSTM dynamically adjusts and learns the places and usage of words.
At a first sight, this looks intimidating. Let’s ignore the internals, but only look at the inputs and outputs of the unit. The network takes three inputs. X_t is the input of the current time step. h_t-1 is the output from the previous LSTM unit and C_t-1 is the “memory” of the previous unit, which I think is the most important input. As for outputs, h_t is the output of the current network. C_t is the memory of the current unit.
Therefore, this single unit makes decision by considering the current input, previous output and previous memory. And it generates a new output and alters its memory.
Below you can see our genres and the number of summaries containing that genre. It is clearly visible that some genres have spikes in numbers while most have a low number of summaries. This creates an inconsistency and lack of knowledge for our model. Thus it lacks accuracy in the low numbered genres.
Our LSTM model output can be seen below.
The accuracy of our classification:
Related Links:
Members:
