2-dimensional |
classifier or regression on two variables |

algo |
non-trivial algorithm implemented |

bernoulli |
Bernoulli (naive Bayes) model used |

bigram |
bigrams considered |

c++ |
written (partially or fully) in C++ |

cnn |
Convolutional Neural Network |

crm-114 |
CRM-114 used |

fasttext |
fasttext used |

feature-engineering |
used more advanced pre-processing, feature engineering etc. |

haskell |
written (partially or fully) in Haskell |

java |
written (partially or fully) in Java |

kenlm |
KenLM used |

k-means |
k-means or its variant used |

knn |
k nearest neighbors |

linear-regression |
linear regression used |

lisp |
written (partially or fully) in Lisp |

lm |
a language model used |

logistic-regression |
logistic regression used |

mert |
MERT (or equivalent) for Moses |

moses |
Moses MT |

multidimensional |
classifier or regression on many variables |

multinomial |
multinomial (naive Bayes) model used |

naive-bayes |
Naive Bayes Classifier used |

neural-network |
neural network used |

n-grams |
n-grams used |

null-model |
null model baseline |

perl |
written (partially or fully) in Perl |

python |
written (partially or fully) in Python 2/3 |

r |
written (partially or fully) in R |

ready-made |
Machine Learning framework/library/toolkit used, algorithm was not implemented by the submitter |

regexp |
handcrafted regular expressions used |

rnn |
Recurrent Neural Network |

ruby |
written (partially or fully) in Ruby |

scikit-learn |
sci-kit learn used |

self-made |
algorithm implemented by the submitter, no framework used |

stupid |
simple, stupid rule-based solution |

temporal |
temporal information taken into account |

trigram |
trigrams considered |

unigram |
only unigrams considered |

vowpal-wabbit |
Vowpal Wabbit used |

word2vec |
Word2Vec |