config.toml

stop-words = "../data/lemur-stopwords.txt"
libsvm-modules = "../deps/libsvm-modules/"
prefix = "../data/"
function-words = "../data/function-words.txt"
punctuation = "../data/sentence-boundaries/sentence-punctuation.txt"
start-exceptions = "../data/sentence-boundaries/sentence-start-exceptions.txt"
end-exceptions = "../data/sentence-boundaries/sentence-end-exceptions.txt"
query-judgements = "../data/ceeaus-qrels.txt"

corpus-type = "line-corpus"
dataset = "20newsgroups"
forward-index = "20news-fwd"
inverted-index = "20news-inv"

[[analyzers]]
method = "ngram-word"
ngram = 1
filter = "default-chain"

[ranker]
method = "bm25"
k1 = 1.2
b = 0.75
k3 = 500

[classifier]
method = "one-vs-all"
[classifier.base]
method = "sgd"
loss = "hinge"
prefix = "sgd-model"

[lda]
inference = "gibbs"
max-iters = 1000
alpha = 1.0
beta = 1.0
topics = 4
model-prefix = "lda-model"

[crf]
prefix = "crf"
treebank = "penn-treebank" # relative to data prefix
corpus = "wsj"
section-size = 99
train-sections = [0, 18]
dev-sections = [19, 21]
test-sections = [22, 24]

[sequence]
prefix = "perceptron-tagger"
treebank = "penn-treebank" # relative to data prefix
corpus = "wsj"
section-size = 99
train-sections = [0, 18]
dev-sections = [19, 21]
test-sections = [22, 24]

[parser]
prefix = "parser"
treebank = "penn-treebank" # relative to data prefix
corpus = "wsj"
section-size = 99
train-sections = [2, 21]
dev-sections = [22, 22]
test-sections = [23, 23]