/**
* Return information about the objects in this Tree.
*
* @param t The tree to examine.
* @return A human-readable String
*/
public static String toDebugStructureString(Tree t) {
StringBuilder sb = new StringBuilder();
String tCl = StringUtils.getShortClassName(t);
String tfCl = StringUtils.getShortClassName(t.treeFactory());
String lCl = StringUtils.getShortClassName(t.label());
String lfCl = StringUtils.getShortClassName(t.label().labelFactory());
Set<String> otherClasses = new HashSet<String>();
for (Tree st : t) {
String stCl = StringUtils.getShortClassName(st);
String stfCl = StringUtils.getShortClassName(st.treeFactory());
String slCl = StringUtils.getShortClassName(st.label());
String slfCl = StringUtils.getShortClassName(st.label().labelFactory());
if (!tCl.equals(stCl)) {
otherClasses.add(stCl);
}
if (!tfCl.equals(stfCl)) {
otherClasses.add(stfCl);
}
if (!lCl.equals(slCl)) {
otherClasses.add(slCl);
}
if (!lfCl.equals(slfCl)) {
otherClasses.add(slfCl);
}
}
sb.append("Tree with root of class ").append(tCl).append(" and factory ").append(tfCl);
sb.append(" with label class ").append(lCl).append(" and factory ").append(lfCl);
if (!otherClasses.isEmpty()) {
sb.append(" with the following classes also found within the tree: ").append(otherClasses);
}
return sb.toString();
}
static String escape(String s) {
StringBuilder sb = new StringBuilder();
for (int i = 0; i < s.length(); i++) {
char c = s.charAt(i);
if (c == '^') sb.append('\\');
sb.append(c);
if (c == '^') sb.append("{}");
}
return sb.toString();
}
protected String historyToString(List history) {
String str = (String) historyToString.get(history);
if (str == null) {
StringBuilder sb = new StringBuilder();
for (int i = 0; i < history.size(); i++) {
sb.append('^');
sb.append(history.get(i));
}
str = sb.toString();
historyToString.put(history, str);
}
return str;
}
public ArrayList<String> getPairsFromSentence(String sentence) {
Collection<TypedDependency> tdl = parseSentenceTDL(sentence);
ArrayList<String> pairs = new ArrayList<String>();
for (TypedDependency td : tdl) {
StringBuilder sb = new StringBuilder();
sb.append(td.gov().originalText());
sb.append(" ");
sb.append(td.dep().originalText());
pairs.add(sb.toString());
}
return pairs;
}
public String project(String tagStr) {
StringBuilder sb = new StringBuilder();
boolean good = true;
for (int pos = 0, len = tagStr.length(); pos < len; pos++) {
char c = tagStr.charAt(pos);
if (c == '-') {
good = true;
} else if (c == '^') {
good = false;
}
if (good) {
sb.append(c);
}
}
String ret = sb.toString();
// System.err.println("TTP mapped " + tagStr + " to " + ret);
return ret;
}
private Distribution<Integer> getSegmentedWordLengthDistribution(Treebank tb) {
// CharacterLevelTagExtender ext = new CharacterLevelTagExtender();
ClassicCounter<Integer> c = new ClassicCounter<Integer>();
for (Iterator iterator = tb.iterator(); iterator.hasNext(); ) {
Tree gold = (Tree) iterator.next();
StringBuilder goldChars = new StringBuilder();
ArrayList goldYield = gold.yield();
for (Iterator wordIter = goldYield.iterator(); wordIter.hasNext(); ) {
Word word = (Word) wordIter.next();
goldChars.append(word);
}
List<HasWord> ourWords = segment(goldChars.toString());
for (int i = 0; i < ourWords.size(); i++) {
c.incrementCount(Integer.valueOf(ourWords.get(i).word().length()));
}
}
return Distribution.getDistribution(c);
}
protected String projectString(String str) {
if (str.indexOf('@') == -1) {
if (str.indexOf('^') == -1) {
return str;
}
return str.substring(0, str.indexOf('^'));
}
StringBuilder sb = new StringBuilder();
sb.append(str.substring(0, str.indexOf(' ')));
if (str.indexOf('^') > -1) {
// sb.append(str.substring(str.indexOf('^'),str.length()));
}
int num = -2;
for (int i = 0; i < str.length(); i++) {
if (str.charAt(i) == ' ') {
num++;
}
}
sb.append(" w " + num);
return sb.toString();
}
private static int treeToLatexEvenHelper(
Tree t,
StringBuilder c,
StringBuilder h,
int n,
int nextN,
int indent,
int curDepth,
int maxDepth) {
StringBuilder sb = new StringBuilder();
for (int i = 0; i < indent; i++) sb.append(" ");
h.append('\n').append(sb);
int tDepth = t.depth();
if (tDepth == 0 && tDepth + curDepth < maxDepth) {
for (int pad = 0; pad < maxDepth - tDepth - curDepth; pad++) {
h.append("{\\ntnode{pad}{}, ");
}
}
h.append("{\\ntnode{z").append(n).append("}{").append(t.label()).append('}');
if (!t.isLeaf()) {
for (int k = 0; k < t.children().length; k++) {
h.append(", ");
c.append("\\nodeconnect{z").append(n).append("}{z").append(nextN).append("}\n");
nextN =
treeToLatexEvenHelper(
t.children()[k], c, h, nextN, nextN + 1, indent + 1, curDepth + 1, maxDepth);
}
}
if (tDepth == 0 && tDepth + curDepth < maxDepth) {
for (int pad = 0; pad < maxDepth - tDepth - curDepth; pad++) {
h.append('}');
}
}
h.append('}');
return nextN;
}
private static int treeToLatexHelper(
Tree t, StringBuilder c, StringBuilder h, int n, int nextN, int indent) {
StringBuilder sb = new StringBuilder();
for (int i = 0; i < indent; i++) sb.append(" ");
h.append('\n').append(sb);
h.append("{\\")
.append(t.isLeaf() ? "" : "n")
.append("tnode{z")
.append(n)
.append("}{")
.append(t.label())
.append('}');
if (!t.isLeaf()) {
for (int k = 0; k < t.children().length; k++) {
h.append(", ");
c.append("\\nodeconnect{z").append(n).append("}{z").append(nextN).append("}\n");
nextN = treeToLatexHelper(t.children()[k], c, h, nextN, nextN + 1, indent + 1);
}
}
h.append('}');
return nextN;
}
/**
* Do max language model markov segmentation. Note that this algorithm inherently tags words as it
* goes, but that we throw away the tags in the final result so that the segmented words are
* untagged. (Note: for a couple of years till Aug 2007, a tagged result was returned, but this
* messed up the parser, because it could use no tagging but the given tagging, which often wasn't
* very good. Or in particular it was a subcategorized tagging which never worked with the current
* forceTags option which assumes that gold taggings are inherently basic taggings.)
*
* @param s A String to segment
* @return The list of segmented words.
*/
private ArrayList<HasWord> segmentWordsWithMarkov(String s) {
int length = s.length();
// Set<String> POSes = (Set<String>) POSDistribution.keySet(); // 1.5
int numTags = POSes.size();
// score of span with initial word of this tag
double[][][] scores = new double[length][length + 1][numTags];
// best (length of) first word for this span with this tag
int[][][] splitBacktrace = new int[length][length + 1][numTags];
// best tag for second word over this span, if first is this tag
int[][][] POSbacktrace = new int[length][length + 1][numTags];
for (int i = 0; i < length; i++) {
for (int j = 0; j < length + 1; j++) {
Arrays.fill(scores[i][j], Double.NEGATIVE_INFINITY);
}
}
// first fill in word probabilities
for (int diff = 1; diff <= 10; diff++) {
for (int start = 0; start + diff <= length; start++) {
int end = start + diff;
StringBuilder wordBuf = new StringBuilder();
for (int pos = start; pos < end; pos++) {
wordBuf.append(s.charAt(pos));
}
String word = wordBuf.toString();
for (String tag : POSes) {
IntTaggedWord itw = new IntTaggedWord(word, tag, wordIndex, tagIndex);
double score = lex.score(itw, 0, word, null);
if (start == 0) {
score += Math.log(initialPOSDist.probabilityOf(tag));
}
scores[start][end][itw.tag()] = score;
splitBacktrace[start][end][itw.tag()] = end;
}
}
}
// now fill in word combination probabilities
for (int diff = 2; diff <= length; diff++) {
for (int start = 0; start + diff <= length; start++) {
int end = start + diff;
for (int split = start + 1; split < end && split - start <= 10; split++) {
for (String tag : POSes) {
int tagNum = tagIndex.indexOf(tag, true);
if (splitBacktrace[start][split][tagNum] != split) {
continue;
}
Distribution<String> rTagDist = markovPOSDists.get(tag);
if (rTagDist == null) {
continue; // this happens with "*" POS
}
for (String rTag : POSes) {
int rTagNum = tagIndex.indexOf(rTag, true);
double newScore =
scores[start][split][tagNum]
+ scores[split][end][rTagNum]
+ Math.log(rTagDist.probabilityOf(rTag));
if (newScore > scores[start][end][tagNum]) {
scores[start][end][tagNum] = newScore;
splitBacktrace[start][end][tagNum] = split;
POSbacktrace[start][end][tagNum] = rTagNum;
}
}
}
}
}
}
int nextPOS = ArrayMath.argmax(scores[0][length]);
ArrayList<HasWord> words = new ArrayList<HasWord>();
int start = 0;
while (start < length) {
int split = splitBacktrace[start][length][nextPOS];
StringBuilder wordBuf = new StringBuilder();
for (int i = start; i < split; i++) {
wordBuf.append(s.charAt(i));
}
String word = wordBuf.toString();
// String tag = tagIndex.get(nextPOS);
// words.add(new TaggedWord(word, tag));
words.add(new Word(word));
if (split < length) {
nextPOS = POSbacktrace[start][length][nextPOS];
}
start = split;
}
return words;
}
// CDM 2007: I wonder what this does differently from segmentWordsWithMarkov???
private ArrayList<TaggedWord> basicSegmentWords(String s) {
int length = s.length();
// Set<String> POSes = (Set<String>) POSDistribution.keySet(); // 1.5
// best score of span
double[][] scores = new double[length][length + 1];
// best (last index of) first word for this span
int[][] splitBacktrace = new int[length][length + 1];
// best tag for word over this span
int[][] POSbacktrace = new int[length][length + 1];
for (int i = 0; i < length; i++) {
Arrays.fill(scores[i], Double.NEGATIVE_INFINITY);
}
// first fill in word probabilities
for (int diff = 1; diff <= 10; diff++) {
for (int start = 0; start + diff <= length; start++) {
int end = start + diff;
StringBuilder wordBuf = new StringBuilder();
for (int pos = start; pos < end; pos++) {
wordBuf.append(s.charAt(pos));
}
String word = wordBuf.toString();
// for (String tag : POSes) { // 1.5
for (Iterator<String> iter = POSes.iterator(); iter.hasNext(); ) {
String tag = iter.next();
IntTaggedWord itw = new IntTaggedWord(word, tag, wordIndex, tagIndex);
double newScore =
lex.score(itw, 0, word, null) + Math.log(lex.getPOSDistribution().probabilityOf(tag));
if (newScore > scores[start][end]) {
scores[start][end] = newScore;
splitBacktrace[start][end] = end;
POSbacktrace[start][end] = itw.tag();
}
}
}
}
// now fill in word combination probabilities
for (int diff = 2; diff <= length; diff++) {
for (int start = 0; start + diff <= length; start++) {
int end = start + diff;
for (int split = start + 1; split < end && split - start <= 10; split++) {
if (splitBacktrace[start][split] != split) {
continue; // only consider words on left
}
double newScore = scores[start][split] + scores[split][end];
if (newScore > scores[start][end]) {
scores[start][end] = newScore;
splitBacktrace[start][end] = split;
}
}
}
}
List<TaggedWord> words = new ArrayList<TaggedWord>();
int start = 0;
while (start < length) {
int end = splitBacktrace[start][length];
StringBuilder wordBuf = new StringBuilder();
for (int pos = start; pos < end; pos++) {
wordBuf.append(s.charAt(pos));
}
String word = wordBuf.toString();
String tag = tagIndex.get(POSbacktrace[start][end]);
words.add(new TaggedWord(word, tag));
start = end;
}
return new ArrayList<TaggedWord>(words);
}