16

我在理解最新版本的斯坦福 NLP 工具中对 coref 解析器所做的更改时遇到了一些麻烦。例如,下面是一个句子和对应的 CorefChainAnnotation:

The atom is a basic unit of matter, it consists of a dense central nucleus surrounded by a cloud of negatively charged electrons.

{1=[1 1, 1 2], 5=[1 3], 7=[1 4], 9=[1 5]}

我不确定我是否理解这些数字的含义。查看源代码也无济于事。

谢谢

4

3 回答 3

17

我一直在使用共指依赖图,并从使用这个问题的另一个答案开始。过了一会儿,虽然我意识到上面的算法并不完全正确。它产生的输出甚至不接近我的修改版本。

对于使用本文的其他人,这是我最终使用的算法,它也过滤掉了自我引用,因为每个代表提及也提到了自己,而且很多提及只引用了自己。

Map<Integer, CorefChain> coref = document.get(CorefChainAnnotation.class);

for(Map.Entry<Integer, CorefChain> entry : coref.entrySet()) {
    CorefChain c = entry.getValue();

    //this is because it prints out a lot of self references which aren't that useful
    if(c.getCorefMentions().size() <= 1)
        continue;

    CorefMention cm = c.getRepresentativeMention();
    String clust = "";
    List<CoreLabel> tks = document.get(SentencesAnnotation.class).get(cm.sentNum-1).get(TokensAnnotation.class);
    for(int i = cm.startIndex-1; i < cm.endIndex-1; i++)
        clust += tks.get(i).get(TextAnnotation.class) + " ";
    clust = clust.trim();
    System.out.println("representative mention: \"" + clust + "\" is mentioned by:");

    for(CorefMention m : c.getCorefMentions()){
        String clust2 = "";
        tks = document.get(SentencesAnnotation.class).get(m.sentNum-1).get(TokensAnnotation.class);
        for(int i = m.startIndex-1; i < m.endIndex-1; i++)
            clust2 += tks.get(i).get(TextAnnotation.class) + " ";
        clust2 = clust2.trim();
        //don't need the self mention
        if(clust.equals(clust2))
            continue;

        System.out.println("\t" + clust2);
    }
}

您的例句的最终输出如下:

representative mention: "a basic unit of matter" is mentioned by:
The atom
it

通常,“原子”最终成为代表性提及,但在这种情况下,这并不奇怪。另一个输出更准确的示例是以下句子:

革命战争发生在 1700 年代,是美国的第一次战争。

产生以下输出:

representative mention: "The Revolutionary War" is mentioned by:
it
the first war in the United States
于 2011-12-16T13:43:58.120 回答
9

第一个数字是一个cluster id(代表token,代表同一个实体),见源代码SieveCoreferenceSystem#coref(Document)。对数超出 CorefChain#toString():

public String toString(){
    return position.toString();
}

其中位置是一组实体提及的位置对(让它们使用CorefChain.getCorefMentions())。这是一个完整代码的示例(在groovy中),它显示了如何从位置获取令牌:

class Example {
    public static void main(String[] args) {
        Properties props = new Properties();
        props.put("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
        props.put("dcoref.score", true);
        pipeline = new StanfordCoreNLP(props);
        Annotation document = new Annotation("The atom is a basic unit of matter, it   consists of a dense central nucleus surrounded by a cloud of negatively charged electrons.");

        pipeline.annotate(document);
        Map<Integer, CorefChain> graph = document.get(CorefChainAnnotation.class);

        println aText

        for(Map.Entry<Integer, CorefChain> entry : graph) {
          CorefChain c =   entry.getValue();                
          println "ClusterId: " + entry.getKey();
          CorefMention cm = c.getRepresentativeMention();
          println "Representative Mention: " + aText.subSequence(cm.startIndex, cm.endIndex);

          List<CorefMention> cms = c.getCorefMentions();
          println  "Mentions:  ";
          cms.each { it -> 
              print aText.subSequence(it.startIndex, it.endIndex) + "|"; 
          }         
        }
    }
}

输出(我不明白's'来自哪里):

The atom is a basic unit of matter, it consists of a dense central nucleus surrounded by a cloud of negatively charged electrons.
ClusterId: 1
Representative Mention: he
Mentions: he|atom |s|
ClusterId: 6
Representative Mention:  basic unit 
Mentions:  basic unit |
ClusterId: 8
Representative Mention:  unit 
Mentions:  unit |
ClusterId: 10
Representative Mention: it 
Mentions: it |
于 2011-07-06T12:42:35.153 回答
0

这些是注释器最近的结果。

  1. [1, 1] 1 原子
  2. [1, 2] 1 物质的基本单位
  3. [1, 3] 1 个
  4. [1, 6] 6 个带负电的电子
  5. [1, 5] 5 带负电的电子云

标记如下:

[Sentence number,'id']  Cluster_no  Text_Associated

属于同一个簇的文本指的是同一个上下文。

于 2017-07-18T07:00:50.817 回答