Search "+Home -Bookshelf +Funny things +Alan Moore +YY +Sociology -Donald Knuth +Probability Theory: The Logic of Science +Math +David MacKay +Science of science +Science +Scientometrics +Books +Information theory +Software engineering +Machine learning +Paper/MacKay1991 +Industry-Academic Partnership +G. Dobínski -Migration +Pointwise mutual information +Paper +Software license +Cross entropy +Class imbalance problem +Word embedding +Continuous embedding +word2vec -Natural language processing"

Positive matches

• 0.049 + - Network geometry
• 0.046 + - Lexical feature selection
• 0.036 + - Graph embedding
• 0.034 + - Class imbalance
• 0.029 + - Interdisciplinary research
• 0.022 + - Text analysis
• 0.017 + - Probability theory
• 0.015 + - Software engineering in research
• 0.012 + - Sentence embedding
• 0.012 + - Software documentation
• 0.012 + - GloVe
• 0.012 + - Policy
• 0.009 + - Edwin Thompson Jaynes
• 0.008 + - Hessian matrix
• 0.008 + - Embedded topic model
• 0.007 + - Science policy
• 0.006 + - Information Theory, Inference, and Learning Algorithms
• 0.006 + - David Feldman
• 0.006 + - Topic model
• 0.006 + - Paper/Tshitoyan2019unsupervised

Negative matches

• 0.005 + - CNN
• 0.004 + - Paper/Gatys2015
• 0.003 + - Residual leanrning
• 0.002 + - Residual Learning
• 0.001 + - BERT
• 0.001 + - String metric
• 0.001 + - Word segmentation
• 0.001 + - Dialog act
• 0.001 + - BookNLP
• 0.001 + - Christopher D. Manning
• 0.001 + - KoNLPy
• 0.001 + - Latent Dirichlet allocation
• 0.001 + - KenLM
• 0.001 + - fastText
• 0.001 + - Long short-term memory
• 0.001 + - Kyunghyun Cho
• 0.001 + - NLTK
• 0.001 + - scispaCy
• 0.001 + - RNN
• 0.001 + - spaCy