Skip to content

Cross entropy for different separation types and different ways to calculate cross entropy

Jump to bottom
hlibbabii edited this page Feb 5, 2019 · 8 revisions
Word No splitting Separators Boundaries
BorderLayout 5.415 <cap> b <sc_sep> order <cc_sep> layout
['0.015', '5.137', '0.067', '1.302', '0.142', '0.016']= 6.680		 <cc> <cap> b order <cc> layout </cc>
['0.052', '0.005', '2.463', '0.081', '0.016', '0.014', '0.025']= 2.657
JMenuBar 11.352 <cap> j <cc_sep> menu <cc_sep> bar
['0.055', '4.950', '0.060', '2.571', '0.125', '1.965']= 9.726		 <cc> <cap> j <cc> menu <cc> bar </cc>
['0.037', '0.006', '3.470', '0.012', '5.903', '0.276', '2.794', '0.553']= 13.052
  1. Introduction
  2. State of the art
  3. Background information
    1. Brief Introduction to language modeling
    2. Brief Introduction to Neural Networks and Deep Learning
    3. Using Recurrent Neural Networks for Language Modeling
    4. Long Short Term Memory Networks
  4. Vocab modeling
    1. Data Gathering and Tokenization
    2. Reducing Vocabulary Size
    3. Preprocess Configurations
    4. Vocabulary modeling evaluation
  5. Language modeling
    1. Neural network architecture
    2. Neural Network Training
    3. Subword aware accuracy and entropy
    4. Neural Cache
    5. Language modeling evaluation
  6. Building classifiers
    1. Generation of labeled data for classification
    2. Transfer learning
    3. Classification parameter hypersearch
    4. Classifier evaluation
  7. Discussion
  8. Future work
  9. Conclusion
  10. Appendix A. Preprocessing Configurations Examples
  11. Appendix B. Subword Representation Examples
Clone this wiki locally