1

从 下载主干代码后http://code.google.com/p/berkeleyaligner/，我将项目添加到我在 Eclipse 上的构建路径中。然后使用下面的代码，我可以提取我从 sourceFile 和 targetFile 中读取的每个句子对的对齐方式。对齐后，如何Alignment从 BerkeleyAligner 读取类型？

import edu.berkeley.nlp.wa.mt.Alignment;
import edu.berkeley.nlp.wa.mt.SentencePair;
import edu.berkeley.nlp.wordAlignment.combine.WordAlignerCombined;
public static void main(String[] args) {
BufferedReader brSrc = new BufferedReader(new FileReader ("sourceFile"));
BufferedReader brTrg = new BufferedReader(new FileReader ("targetFile"));
while ((currentSrcLine = brSrc.readLine()) !=null) {
    String currentTrgLine = brTrg.readline();
    // Reads into BerkeleyAligner SentencePair format.
    SentencePair src2trg = new SentencePair(sentCounter, params.get("source"),
        Arrays.asList(srcLine.split(" ")), Arrays.asList(trgLine.split(" ")));
    // Generate Alignment type from SentencePair
    WordAlignerCombined aligner;
    Alignment alignedPair = aligner.alignSentencePair(src2trg);
    // How do i print out the Alignment???
    }
}

例如源文件：

this is the first line in the textfile.
that is the second line.
foo bar likes to eat bar foo.

例如目标文件：

Dies ist die erste Textzeile in der Datei.
das ist die zweite Zeile.
foo bar gerne bar foo essen.
4

1 回答 1

1

打印吉萨。对齐有一个方法：

public void writeGIZA(PrintWriter out, int idx)

吉萨是：

"# sentence pair (%d) source length %d target length %d alignment score : 0\n"
"NULL ({ %s })"
" %s ({ %s })" (englishSentence.get(i), StrUtils.join(alignments))

idx只是句子对 id。

out就是你想打印的地方。

于 2012-01-02T23:16:05.597 回答