有谁知道在哪里可以找到一点如何在 java 或 scala 中使用 dbpedia 聚光灯？或者任何人都可以解释它是如何完成的？我找不到这方面的任何信息...
问问题
3886 次
4 回答
4
你需要下载 dbpedia Spotlight（jar 文件），然后你可以使用接下来的两个类（作者 pablomendes）我只做一些改变。
public class db extends AnnotationClient {
//private final static String API_URL = "http://jodaiber.dyndns.org:2222/";
private static String API_URL = "http://spotlight.dbpedia.org:80/";
private static double CONFIDENCE = 0.0;
private static int SUPPORT = 0;
private static String powered_by ="non";
private static String spotter ="CoOccurrenceBasedSelector";//"LingPipeSpotter"=Annotate all spots
//AtLeastOneNounSelector"=No verbs and adjs.
//"CoOccurrenceBasedSelector" =No 'common words'
//"NESpotter"=Only Per.,Org.,Loc.
private static String disambiguator ="Default";//Default ;Occurrences=Occurrence-centric;Document=Document-centric
private static String showScores ="yes";
@SuppressWarnings("static-access")
public void configiration(double CONFIDENCE,int SUPPORT,
String powered_by,String spotter,String disambiguator,String showScores){
this.CONFIDENCE=CONFIDENCE;
this.SUPPORT=SUPPORT;
this.powered_by=powered_by;
this.spotter=spotter;
this.disambiguator=disambiguator;
this.showScores=showScores;
}
public List<DBpediaResource> extract(Text text) throws AnnotationException {
LOG.info("Querying API.");
String spotlightResponse;
try {
String Query=API_URL + "rest/annotate/?" +
"confidence=" + CONFIDENCE
+ "&support=" + SUPPORT
+ "&spotter=" + spotter
+ "&disambiguator=" + disambiguator
+ "&showScores=" + showScores
+ "&powered_by=" + powered_by
+ "&text=" + URLEncoder.encode(text.text(), "utf-8");
LOG.info(Query);
GetMethod getMethod = new GetMethod(Query);
getMethod.addRequestHeader(new Header("Accept", "application/json"));
spotlightResponse = request(getMethod);
} catch (UnsupportedEncodingException e) {
throw new AnnotationException("Could not encode text.", e);
}
assert spotlightResponse != null;
JSONObject resultJSON = null;
JSONArray entities = null;
try {
resultJSON = new JSONObject(spotlightResponse);
entities = resultJSON.getJSONArray("Resources");
} catch (JSONException e) {
//throw new AnnotationException("Received invalid response from DBpedia Spotlight API.");
}
LinkedList<DBpediaResource> resources = new LinkedList<DBpediaResource>();
if(entities!=null)
for(int i = 0; i < entities.length(); i++) {
try {
JSONObject entity = entities.getJSONObject(i);
resources.add(
new DBpediaResource(entity.getString("@URI"),
Integer.parseInt(entity.getString("@support"))));
} catch (JSONException e) {
LOG.error("JSON exception "+e);
}
}
return resources;
}
}
二等
/**
* @author pablomendes
*/
public abstract class AnnotationClient {
public Logger LOG = Logger.getLogger(this.getClass());
private List<String> RES = new ArrayList<String>();
// Create an instance of HttpClient.
private static HttpClient client = new HttpClient();
public List<String> getResu(){
return RES;
}
public String request(HttpMethod method) throws AnnotationException {
String response = null;
// Provide custom retry handler is necessary
method.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,
new DefaultHttpMethodRetryHandler(3, false));
try {
// Execute the method.
int statusCode = client.executeMethod(method);
if (statusCode != HttpStatus.SC_OK) {
LOG.error("Method failed: " + method.getStatusLine());
}
// Read the response body.
byte[] responseBody = method.getResponseBody(); //TODO Going to buffer response body of large or unknown size. Using getResponseBodyAsStream instead is recommended.
// Deal with the response.
// Use caution: ensure correct character encoding and is not binary data
response = new String(responseBody);
} catch (HttpException e) {
LOG.error("Fatal protocol violation: " + e.getMessage());
throw new AnnotationException("Protocol error executing HTTP request.",e);
} catch (IOException e) {
LOG.error("Fatal transport error: " + e.getMessage());
LOG.error(method.getQueryString());
throw new AnnotationException("Transport error executing HTTP request.",e);
} finally {
// Release the connection.
method.releaseConnection();
}
return response;
}
protected static String readFileAsString(String filePath) throws java.io.IOException{
return readFileAsString(new File(filePath));
}
protected static String readFileAsString(File file) throws IOException {
byte[] buffer = new byte[(int) file.length()];
@SuppressWarnings("resource")
BufferedInputStream f = new BufferedInputStream(new FileInputStream(file));
f.read(buffer);
return new String(buffer);
}
static abstract class LineParser {
public abstract String parse(String s) throws ParseException;
static class ManualDatasetLineParser extends LineParser {
public String parse(String s) throws ParseException {
return s.trim();
}
}
static class OccTSVLineParser extends LineParser {
public String parse(String s) throws ParseException {
String result = s;
try {
result = s.trim().split("\t")[3];
} catch (ArrayIndexOutOfBoundsException e) {
throw new ParseException(e.getMessage(), 3);
}
return result;
}
}
}
public void saveExtractedEntitiesSet(String Question, LineParser parser, int restartFrom) throws Exception {
String text = Question;
int i=0;
//int correct =0 ; int error = 0;int sum = 0;
for (String snippet: text.split("\n")) {
String s = parser.parse(snippet);
if (s!= null && !s.equals("")) {
i++;
if (i<restartFrom) continue;
List<DBpediaResource> entities = new ArrayList<DBpediaResource>();
try {
entities = extract(new Text(snippet.replaceAll("\\s+"," ")));
System.out.println(entities.get(0).getFullUri());
} catch (AnnotationException e) {
// error++;
LOG.error(e);
e.printStackTrace();
}
for (DBpediaResource e: entities) {
RES.add(e.uri());
}
}
}
}
public abstract List<DBpediaResource> extract(Text text) throws AnnotationException;
public void evaluate(String Question) throws Exception {
evaluateManual(Question,0);
}
public void evaluateManual(String Question, int restartFrom) throws Exception {
saveExtractedEntitiesSet(Question,new LineParser.ManualDatasetLineParser(), restartFrom);
}
}
主要的（）
public static void main(String[] args) throws Exception {
String Question ="Is the Amazon river longer than the Nile River?";
db c = new db ();
c.configiration(0.0, 0, "non", "CoOccurrenceBasedSelector", "Default", "yes");
System.out.println("resource : "+c.getResu());
}
于 2013-03-27T09:53:12.280 回答
4
DBpedia Spotlight wiki页面将是一个很好的起点。
而且我相信安装页面列出了使用该应用程序的最流行的方式（使用 jar 或设置 Web 服务）。
它包括有关在您自己的安装中使用 Java/Scala API或调用 Web 服务的说明。
需要下载一些额外的数据来运行您自己的服务器以获得全面服务，这是为自己煮咖啡的好时机。
于 2012-05-21T19:03:42.487 回答
0
我只是为您的答案添加了一个小修复。如果您添加evaluate方法调用，您的代码正在运行：
public static void main(String[] args) throws Exception {
String question = "Is the Amazon river longer than the Nile River?";
db c = new db ();
c.configiration(0.0, 0, "non", "CoOccurrenceBasedSelector", "Default", "yes");
c.evaluate(question);
System.out.println("resource : "+c.getResu());
}
胺
于 2013-12-15T15:30:20.653 回答
0
在阿德尔的回答request中的第二类（AnnotationClient）的方法中，作者巴勃罗·门德斯还没说完
TODO Going to buffer response body of large or unknown size. Using getResponseBodyAsStream instead is recommended.
这是一个烦人的警告，需要通过替换来删除
byte[] responseBody = method.getResponseBody(); //TODO Going to buffer response body of large or unknown size. Using getResponseBodyAsStream instead is recommended.
// Deal with the response.
// Use caution: ensure correct character encoding and is not binary data
response = new String(responseBody);
和
Reader in = new InputStreamReader(method.getResponseBodyAsStream(), "UTF-8");
StringWriter writer = new StringWriter();
org.apache.commons.io.IOUtils.copy(in, writer);
response = writer.toString();
于 2017-03-02T09:33:26.353 回答