corpus_example.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE Corpus SYSTEM "ntumc.dtd">
<!-- A valid XML contains one Corpus element (the root) -->
<!-- It contains at least one document. If it's a multilingual corpus,
     it cointains all documents with progressive ids. When importing
     into NTUMC, the language is inferred at the Document level.
     The attribute "language" in Corpus helps the parser detect
     whether the language of the documents is going to change.    -->
<Corpus corpusID="cp1"
        title="Example of multilingual corpus"
        language="multilingual">
  <Document docID="d1"
            doc="text"
            language="eng"
            title="A title"
            subtitle=""
            url="">
    <Sentence sid="s1"
              sent="The beautiful woman">
      <Word  wid="w1"
             pos="DET"
             lemma="the"
             surface_form="The"
             cfrom="0"
             cto="2"/>
      <Word  wid="w2"
             pos="ADJ"
             lemma="beautiful"
             surface_form="beautiful"
             cfrom="4"
             cto="12"/>
      <Word  wid="w3"
             pos="NOUN"
             lemma="woman"
             surface_form="woman"
             cfrom="14"
             cto="18"/>
      <Concept cid="c1" wid="w3" synset_tag="10787470-n">
	<Tag category="sentiment" value="0.8"/>
      </Concept>
      <Chunk chid="ch1" wid="w2 w3">
	<Tag category="sentiment" value="0.8"/>
      </Chunk>
    </Sentence>
  </Document>
  <Document docID="d2"
            doc="text"
            language="ita"
            title="Un titolo"
            subtitle=""
            url="">
    <Sentence sid="s2"
              sent="La donna">
      <Word  wid="w4"
             pos="DET"
             lemma="il"
             surface_form="La"
             cfrom="0"
             cto="1"/>
      <Word  wid="w5"
             pos="NOUN"
             lemma="donna"
             surface_form="donna"
             cfrom="2"
             cto="6"/>
      <Concept cid="c2" wid="w5" synset_tag="10787470-n"/>
    </Sentence>
  </Document>
  <Document docID="d3"
            doc="text"
            language="spa"
            title="Un título">
    <Sentence sid="s3"
              sent="La mulier">
      <Word  wid="w6"
             pos="DET"
             lemma="el"
             surface_form="La"
             cfrom="0"
             cto="1"/>
      <Word  wid="w7"
             pos="NOUN"
             lemma="mulier"
             surface_form="mulier"
             cfrom="2"
             cto="7"/>
      <Concept cid="c3" wid="w7" synset_tag="10787470-n"/>
    </Sentence>
  </Document>
  <Alignment>
    <DocAlignment docID="d1 d2 d3"/>
    <SentAlignment sid_from="s1" sid_to="s2"/>
    <SentAlignment sid_from="s1" sid_to="s3"/>
    <SentAlignment sid_from="s2" sid_to="s1"/>
    <SentAlignment sid_from="s2" sid_to="s3"/>
    <SentAlignment sid_from="s3" sid_to="s1"/>
    <SentAlignment sid_from="s3" sid_to="s2"/>
    <WordAlignment wid_from="w3"  wid_to="w5"/>
    <WordAlignment wid_from="w3"  wid_to="w7"/>
    <ConceptAlignment cid_from="c1" cid_to="c2"/>
    <ConceptAlignment cid_from="c1" cid_to="c3"/>
  </Alignment>
</Corpus>