Lucene 4.9中的BM25

Question

我正在和Lucene的BM25Similarity类((链接) )做斗争。网络上提供的所有示例都提到了较早的实现(链接)。我请求一个指针，如何修改下面的标准玩具示例，以包括BM25相似性(创建索引和执行搜索)。

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

import java.io.IOException;

public class HelloLucene {
  public static void main(String[] args) throws IOException, ParseException {
    // Specify the analyzer for tokenizing text.
    // The same analyzer should be used for indexing and searching
    StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_4_9);

    // Create the index
    Directory index = new RAMDirectory();

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_9, analyzer);

    IndexWriter w = new IndexWriter(index, config);
    addDoc(w, "Lucene in Action", "193398817");
    addDoc(w, "Lucene for Dummies", "55320055Z");
    addDoc(w, "Managing Gigabytes", "55063554A");
    addDoc(w, "The Art of Computer Science", "9900333X");
    w.close();

    // Query
    String querystr = args.length > 0 ? args[0] : "lucene";

    // the "title" arg specifies the default field to use
    // when no field is explicitly specified in the query.
    Query q = new QueryParser(Version.LUCENE_4_9, "title", analyzer).parse(querystr);

    // Search
    int hitsPerPage = 10;
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
    searcher.search(q, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;

    // Display results
    System.out.println("Found " + hits.length + " hits.");
    for(int i=0;i<hits.length;++i) {
      int docId = hits[i].doc;
      Document d = searcher.doc(docId);
      System.out.println((i + 1) + ". " + d.get("isbn") + "\t" + d.get("title"));
    }
    reader.close();
  }

  private static void addDoc(IndexWriter w, String title, String isbn) throws IOException {
    Document doc = new Document();
    doc.add(new TextField("title", title, Field.Store.YES));

    // use a string field for isbn because we don't want it tokenized
    doc.add(new StringField("isbn", isbn, Field.Store.YES));
    w.addDocument(doc);
  }
}

Answer 1

您只需要在IndexSearcher中设置相似度：

searcher.setSimilarity(new BM25Similarity(1.2, 0.75));

和IndexWriterConfig：

config.setSimilarity(new BM25Similarity(1.2, 0.75));