斯坦福大学的中国学术

Question

中国的斯坦福CoreNLP包是否能够检测成语和成语（格言/谚语/惯用语（例如冰冻三尺，非一日之寒））？

Answer 1

也很好！它真的很棒！
以下是由Stanford-NLP管道（中国模型）生成的：tokenize，ssplit，pos，lemma，ner

[
   [
      {
         "category2":null,
         "offset-begin":"0",
         "ner2":"O",
         "lemma2":"冰冻三尺",
         "word2":null,
         "index":"1",
         "index2":"1",
         "lemma":"冰冻三尺",
         "offset-begin2":"null",
         "tag2":"",
         "originalText":"",
         "offset-end":"4",
         "answer":null,
         "pos":"VV",
         "offset-end2":"null",
         "ner":"O",
         "tag":"VV",
         "originalText2":null,
         "category":null,
         "word":"冰冻三尺",
         "value":"冰冻三尺"
      },
      {
         "category2":null,
         "offset-begin":"4",
         "ner2":"O",
         "lemma2":"，",
         "word2":null,
         "index":"2",
         "index2":"2",
         "lemma":"，",
         "offset-begin2":"null",
         "tag2":"",
         "originalText":"",
         "offset-end":"5",
         "answer":null,
         "pos":"PU",
         "offset-end2":"null",
         "ner":"O",
         "tag":"PU",
         "originalText2":null,
         "category":null,
         "word":"，",
         "value":"，"
      },
      {
         "category2":null,
         "offset-begin":"5",
         "ner2":"O",
         "lemma2":"非一日之寒",
         "word2":null,
         "index":"3",
         "index2":"3",
         "lemma":"非一日之寒",
         "offset-begin2":"null",
         "tag2":"",
         "originalText":"",
         "offset-end":"10",
         "answer":null,
         "pos":"VV",
         "offset-end2":"null",
         "ner":"O",
         "tag":"VV",
         "originalText2":null,
         "category":null,
         "word":"非一日之寒",
         "value":"非一日之寒"
      }
   ]
]