From 6c633160f9d1c71bb65144903dda89df0c7232f7 Mon Sep 17 00:00:00 2001 From: Alessandro Suglia Date: Mon, 29 May 2017 15:08:25 +0200 Subject: [PATCH 1/3] DBpedia Spotlight Added support for the 'types' parameter in order to restrict annotations specific types. --- .../dkm/pikes/twm/DBpediaSpotlightAnnotate.java | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java b/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java index b175aa36b..811b36ea4 100644 --- a/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java +++ b/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java @@ -1,10 +1,7 @@ package eu.fbk.dkm.pikes.twm; -import com.google.common.base.Charsets; -import com.google.common.io.Files; import org.codehaus.jackson.map.ObjectMapper; -import java.io.File; import java.util.*; /** @@ -19,20 +16,24 @@ public class DBpediaSpotlightAnnotate extends Linking { private static String LABEL = "dbpedia-annotate"; private String confidence; + private String allowedTypes; public static final String DBPS_ADDRESS = "http://spotlight.sztaki.hu:2222/rest"; public static final double DBPS_MIN_CONFIDENCE = 0.33; public DBpediaSpotlightAnnotate(Properties properties) { super(properties, properties.getProperty("address", DBPS_ADDRESS) + "/annotate"); confidence = properties.getProperty("min_confidence", Double.toString(DBPS_MIN_CONFIDENCE)); + allowedTypes = properties.getProperty("types", null); } public List tag(String text) throws Exception { - ArrayList ret = new ArrayList<>(); Map pars = new HashMap<>(); pars.put("confidence", confidence); + if (allowedTypes != null) { + pars.put("types", allowedTypes); + } pars.put("text", text); Map userData; @@ -67,16 +68,14 @@ public List tag(String text) throws Exception { public static void main(String[] args) { Properties properties = new Properties(); - properties.setProperty("address", "https://knowledgestore2.fbk.eu/dbps/rest/annotate"); - properties.setProperty("use_proxy", "0"); - properties.setProperty("proxy_url", "proxy.fbk.eu"); - properties.setProperty("proxy_port", "3128"); + properties.setProperty("address", "http://model.dbpedia-spotlight.org/en"); properties.setProperty("min_confidence", "0.05"); + properties.setProperty("types", "Drug,Disease,Chemical_compound"); properties.setProperty("timeout", "2000"); DBpediaSpotlightAnnotate s = new DBpediaSpotlightAnnotate(properties); try { - String text = Files.toString(new File("/Users/alessio/Desktop/elastic/test-dbps.txt"), Charsets.UTF_8); + String text = "My doctors suggests to me to take a pill of Aspirin."; List tags = s.tag(text); for (LinkingTag tag : tags) { System.out.println(tag); From 9f20260bd589689ead3ca282231f22f4338af9a1 Mon Sep 17 00:00:00 2001 From: Alessandro Suglia Date: Mon, 29 May 2017 15:12:09 +0200 Subject: [PATCH 2/3] Minor improvements. --- .../dkm/pikes/twm/DBpediaSpotlightAnnotate.java | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java b/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java index 811b36ea4..ab161d6cf 100644 --- a/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java +++ b/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java @@ -4,21 +4,13 @@ import java.util.*; -/** - * Created with IntelliJ IDEA. - * User: alessio - * Date: 21/07/14 - * Time: 17:15 - * To change this template use File | Settings | File Templates. - */ - public class DBpediaSpotlightAnnotate extends Linking { private static String LABEL = "dbpedia-annotate"; private String confidence; private String allowedTypes; - public static final String DBPS_ADDRESS = "http://spotlight.sztaki.hu:2222/rest"; - public static final double DBPS_MIN_CONFIDENCE = 0.33; + private static final String DBPS_ADDRESS = "http://spotlight.sztaki.hu:2222/rest"; + private static final double DBPS_MIN_CONFIDENCE = 0.33; public DBpediaSpotlightAnnotate(Properties properties) { super(properties, properties.getProperty("address", DBPS_ADDRESS) + "/annotate"); @@ -75,7 +67,7 @@ public static void main(String[] args) { DBpediaSpotlightAnnotate s = new DBpediaSpotlightAnnotate(properties); try { - String text = "My doctors suggests to me to take a pill of Aspirin."; + String text = "My doctor has suggested to take a pill of Aspirin."; List tags = s.tag(text); for (LinkingTag tag : tags) { System.out.println(tag); From 56b6972de93c6e94020ade0eff83daa78acde4f9 Mon Sep 17 00:00:00 2001 From: "alessandro.suglia" Date: Mon, 19 Jun 2017 13:22:50 +0200 Subject: [PATCH 3/3] Fixed default DBpedia Spotlight endpoint. --- .../java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java b/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java index ab161d6cf..c8ccc6d70 100644 --- a/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java +++ b/pikes-twm/src/main/java/eu/fbk/dkm/pikes/twm/DBpediaSpotlightAnnotate.java @@ -9,7 +9,7 @@ public class DBpediaSpotlightAnnotate extends Linking { private static String LABEL = "dbpedia-annotate"; private String confidence; private String allowedTypes; - private static final String DBPS_ADDRESS = "http://spotlight.sztaki.hu:2222/rest"; + public static final String DBPS_ADDRESS = "http://model.dbpedia-spotlight.org/en"; private static final double DBPS_MIN_CONFIDENCE = 0.33; public DBpediaSpotlightAnnotate(Properties properties) {