Skip to content
Snippets Groups Projects
Commit 7257b205 authored by Sebastian Hellmann's avatar Sebastian Hellmann
Browse files

abstracts should be working

parent f91f905a
No related branches found
No related tags found
No related merge requests found
......@@ -16,7 +16,40 @@ languages=ro
# extractor class names starting with "." are prefixed by "org.dbpedia.extraction.mappings"
extractors=.MappingExtractor,.RedirectExtractor
#extractors=.NifExtractor,.MappingExtractor
extractors=.MappingExtractor
uri-policy.iri=generic:en; xml-safe-predicates:*
format.ttl.bz2=turtle-triples;uri-policy.iri
mwc-apiUrl=https://{{LANG}}.wikipedia.org/w/api.php
mwc-maxRetries=5
mwc-connectMs=4000
mwc-readMs=30000
mwc-sleepFactor=2000
#parameters specific for the abstract extraction
abstract-query=&format=xml&action=query&prop=extracts&exintro=&explaintext=&titles=%s
# the tag path of the XML tags under which the result is expected
abstract-tags=api,query,pages,page,extract
# the properties used to specify long- and short abstracts (should not change)
short-abstracts-property=rdfs:comment
long-abstracts-property=abstract
# the short abstract is at least this long
short-abstract-min-length=200
#parameters specific to the nif extraction
#only extract abstract (not the whole page)
nif-extract-abstract-only=false
#the request query string
nif-query=&format=xml&action=parse&prop=text&page=%s&pageid=%d
#the xml path of the response
nif-tags=api,parse,text
# will leave out the long and short abstract datasets
nif-isTestRun=false
# will write all anchor texts for each nif instance
nif-write-anchor=true
# write only the anchor text for link instances
nif-write-link-anchor=true
#extractors.ar=.MappingExtractor,.TopicalConceptsExtractor
#
......
# NOTE: this properties files is imported in every extraction process and contains general parameters which only have to be set once for every release
# The DBpedia version to be extracted (in this format: YYYY-MM)
dbpedia-version=2018-10
# SH Note: leaving it blank takes latest.
dbpedia-version=
# Replace with your Wikipedia dump download directory (should not change over the course of a release)
# base-dir=/data/extraction/wikidumps/
......@@ -91,3 +92,7 @@ summarize-exceptions=true
# Options for the SparkExtraction
spark-master=local[32]
spark-local-dir=/data/extraction/spark.local.dir/
###########################
## Abstract and NIF extraction
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment