static

in opennlp-tools/src/main/java/opennlp/tools/postag/POSTagFormatMapper.java [40:113]


  static {
    /*
     * This is a conversion table to convert PENN to UD format as described in
     * https://universaldependencies.org/tagset-conversion/en-penn-uposf.html
     */
    CONVERSION_TABLE_PENN_TO_UD.put("#", "SYM");
    CONVERSION_TABLE_PENN_TO_UD.put("$", "SYM");
    CONVERSION_TABLE_PENN_TO_UD.put("''", "PUNCT");
    CONVERSION_TABLE_PENN_TO_UD.put(",", "PUNCT");
    CONVERSION_TABLE_PENN_TO_UD.put("-LRB-", "PUNCT");
    CONVERSION_TABLE_PENN_TO_UD.put("-RRB-", "PUNCT");
    CONVERSION_TABLE_PENN_TO_UD.put(".", "PUNCT");
    CONVERSION_TABLE_PENN_TO_UD.put(":", "PUNCT");
    CONVERSION_TABLE_PENN_TO_UD.put("AFX", "ADJ");
    CONVERSION_TABLE_PENN_TO_UD.put("CC", "CCONJ");
    CONVERSION_TABLE_PENN_TO_UD.put("CD", "NUM");
    CONVERSION_TABLE_PENN_TO_UD.put("DT", "DET");
    CONVERSION_TABLE_PENN_TO_UD.put("EX", "PRON");
    CONVERSION_TABLE_PENN_TO_UD.put("FW", "X");
    CONVERSION_TABLE_PENN_TO_UD.put("HYPH", "PUNCT");
    CONVERSION_TABLE_PENN_TO_UD.put("IN", "ADP");
    CONVERSION_TABLE_PENN_TO_UD.put("JJ", "ADJ");
    CONVERSION_TABLE_PENN_TO_UD.put("JJR", "ADJ");
    CONVERSION_TABLE_PENN_TO_UD.put("JJS", "ADJ");
    CONVERSION_TABLE_PENN_TO_UD.put("LS", "X");
    CONVERSION_TABLE_PENN_TO_UD.put("MD", "VERB");
    CONVERSION_TABLE_PENN_TO_UD.put("NIL", "X");
    CONVERSION_TABLE_PENN_TO_UD.put("NN", "NOUN");
    CONVERSION_TABLE_PENN_TO_UD.put("NNP", "PROPN");
    CONVERSION_TABLE_PENN_TO_UD.put("NNPS", "PROPN");
    CONVERSION_TABLE_PENN_TO_UD.put("NNS", "NOUN");
    CONVERSION_TABLE_PENN_TO_UD.put("PDT", "DET");
    CONVERSION_TABLE_PENN_TO_UD.put("POS", "PART");
    CONVERSION_TABLE_PENN_TO_UD.put("PRP", "PRON");
    CONVERSION_TABLE_PENN_TO_UD.put("PRP$", "DET");
    CONVERSION_TABLE_PENN_TO_UD.put("RB", "ADV");
    CONVERSION_TABLE_PENN_TO_UD.put("RBR", "ADV");
    CONVERSION_TABLE_PENN_TO_UD.put("RBS", "ADV");
    CONVERSION_TABLE_PENN_TO_UD.put("RP", "ADP");
    CONVERSION_TABLE_PENN_TO_UD.put("SYM", "SYM");
    CONVERSION_TABLE_PENN_TO_UD.put("TO", "PART");
    CONVERSION_TABLE_PENN_TO_UD.put("UH", "INTJ");
    CONVERSION_TABLE_PENN_TO_UD.put("VB", "VERB");
    CONVERSION_TABLE_PENN_TO_UD.put("VBD", "VERB");
    CONVERSION_TABLE_PENN_TO_UD.put("VBG", "VERB");
    CONVERSION_TABLE_PENN_TO_UD.put("VBN", "VERB");
    CONVERSION_TABLE_PENN_TO_UD.put("VBP", "VERB");
    CONVERSION_TABLE_PENN_TO_UD.put("VBZ", "VERB");
    CONVERSION_TABLE_PENN_TO_UD.put("WDT", "DET");
    CONVERSION_TABLE_PENN_TO_UD.put("WP", "PRON");
    CONVERSION_TABLE_PENN_TO_UD.put("WP$", "DET");
    CONVERSION_TABLE_PENN_TO_UD.put("WRB", "ADV");

    /*
     * Note: The back conversion might lose information.
     */
    CONVERSION_TABLE_UD_TO_PENN.put("ADJ", "JJ");
    CONVERSION_TABLE_UD_TO_PENN.put("ADP", "IN");
    CONVERSION_TABLE_UD_TO_PENN.put("ADV", "RB");
    CONVERSION_TABLE_UD_TO_PENN.put("AUX", "MD");
    CONVERSION_TABLE_UD_TO_PENN.put("CCONJ", "CC");
    CONVERSION_TABLE_UD_TO_PENN.put("DET", "DT");
    CONVERSION_TABLE_UD_TO_PENN.put("INTJ", "UH");
    CONVERSION_TABLE_UD_TO_PENN.put("NOUN", "NN");
    CONVERSION_TABLE_UD_TO_PENN.put("NUM", "CD");
    CONVERSION_TABLE_UD_TO_PENN.put("PART", "RP");
    CONVERSION_TABLE_UD_TO_PENN.put("PRON", "PRP");
    CONVERSION_TABLE_UD_TO_PENN.put("PROPN", "NNP");
    CONVERSION_TABLE_UD_TO_PENN.put("PUNCT", ".");
    CONVERSION_TABLE_UD_TO_PENN.put("SCONJ", "IN");
    CONVERSION_TABLE_UD_TO_PENN.put("SYM", "SYM");
    CONVERSION_TABLE_UD_TO_PENN.put("VERB", "VB");
    CONVERSION_TABLE_UD_TO_PENN.put("X", "FW");
  }