# Config file for event chains pipeline

PIPELINE_NAME=gigaword-nyt
HUMAN_READABLE_NAME="Gigaword, NYT"

# Point to a script that will extract the input text for us
INPUT_EXTRACTOR=1-parse/preprocess/extract_gigaword.sh
# This is specific to Gigaword, used by the input extractor
GIGAWORD_FILES=(/usr/groups/corpora-cds/gigaword_eng/data/nyt_eng/*.gz)

# Number of processes to use in any stage
PROCESSES=12
