For all models: learning Rate 0.1; epochs 10; vocab size = 300K unless otherwise stated

== fastText model using 50-dimensional embeddings but no pre-trained embeddings; minCount == 10 (vocab size = 89k) ==
Precision: 0.847 micro; 0.829 macro
Recall: 0.677 micro; 0.601 macro
F1: 0.745 micro; 0.690 macro
PR-AUC: 0.967 micro; 0.959 macro
Avg pre.: 0.813 micro; 0.762 macro

== fastText model using pretrained 50-dimensional skipgram fastText embeddings (with further fine-tuning) ==
Precision: 0.842 micro; 0.824 macro
Recall: 0.731 micro; 0.678 macro
F1: 0.780 micro; 0.741 macro
PR-AUC: 0.974 micro; 0.972 macro
Avg pre.: 0.839 micro; 0.801 macro

== Keras model using 50-dimensional skipgram fastText embeddings with no fine-tuning ==
Precision: 0.738 micro; 0.690 macro
Recall: 0.326 micro; 0.239 macro
F1: 0.430 micro; 0.334 macro
Avg pre.: 0.615 micro; 0.517 macro

== Keras model using fastText-finetuned 50-dimensional skipgram fastText embeddings with no additional fine-tuning == 
Precision: 0.835 micro; 0.809 macro
Recall: 0.505 micro; 0.395 macro
F1: 0.609 micro; 0.511 macro
Avg pre.: 0.756 micro; 0.690 macro

import fasttext
import math
import numpy as np

def sigmoid(x):
   return 1 / (1 + math.exp(-x))

def standard_fasttext(m, input_str, threshold=0.5):
   # get all fasttext predictions above threshold for input data
   print("Normal fasttext prediction: {0}".format([(l.replace('__label__', ''), '{0:.3f}'.format(s)) for l,s in zip(*m.predict(input_str, k=-1)) if s >= threshold]))

def manual_fasttext(m, input_str, threshold=0.5):
   # run fasttext model "manually"
   # 1) average together input word embeddings for document vector
   #    ignore OOV words
   #    add end-of-sentence token ('</s>') to input data
   docvec = np.average([m.get_word_vector(w) for w in input_str.split() if w in m.words] + [m.get_word_vector('</s>')], axis=0)
   
   # 2) take dot product of model weights matrix (64 x 50) and document vector (50, 1) to get output (64, 1) vector
   raw_out = np.dot(m.get_output_matrix(), docvec)
   
   # 3) convert these values to probabilities by passing each through a sigmoid function
   pro_out = [sigmoid(s) for s in list(raw_out)]
   
   # 4) get sorted rank of predicted labels
   top_k = np.argsort(pro_out)[::-1]
   
   # 5) show results above threshold
   print("Manual fasttext prediction:", [(m.get_labels()[i].replace('__label__', ''), '{0:.3f}'.format(pro_out[i])) for i in top_k if pro_out[i] >= threshold])

# example below is Galapagos (video game): https://www.wikidata.org/wiki/Q16981582
# you'll note a small difference in output probabilities that presumably comes from rounding errors somewhere
# in all my testing, while it will affect the ranking of high confidence topics like below, 
# I never saw it grow larger than a ~0.001 difference

>>> m = fasttext.load_model('model.bin')
>>> input_str = 'P577 P31 Q7889 P404 Q208850 P1933 P400 Q1406 P136 Q270948 P495 Q30 P123 Q173941'
>>> threshold = 0.02  # note: normally this would be 0.5 but I set it low for debugging purposes

>>> standard_fasttext(m, input_str, threshold=0.5)
Normal fasttext prediction: [('Culture.Media.Media*', '1.000'), ('Culture.Media.Video_games', '1.000'), ('Culture.Internet_culture', '1.000'), ('STEM.STEM*', '0.024'), ('STEM.Technology', '0.021'), ('Culture.Media.Software', '0.020')]

>>> manual_fasttext(m, input_str, threshold=threshold)
Manual fasttext prediction: [('Culture.Media.Video_games', '1.000'), ('Culture.Internet_culture', '1.000'), ('Culture.Media.Media*', '1.000'), ('STEM.STEM*', '0.025'), ('STEM.Technology', '0.021'), ('Culture.Media.Software', '0.021')]