public String getAnnotatedString(String text, boolean standardized) throws Exception { String ans = ""; TextAnnotation ta = taBuilder.createTextAnnotation(text); List<QuantSpan> quantSpans = getSpans(text, standardized, null); int quantIndex = 0; for (int i = 0; i < ta.size(); ++i) { if (quantSpans.get(quantIndex).start == ta.getTokenCharacterOffset(i).getFirst()) { ans += " [ "; } ans += ta.getToken(i) + " "; if (quantSpans.get(quantIndex).end == ta.getTokenCharacterOffset(i).getSecond()) { ans += " ] " + quantSpans.get(quantIndex) + " "; if (quantIndex < quantSpans.size() - 1) quantIndex++; } } return ans; }
public String getAnnotatedString(String text, boolean standardized) throws Exception { String ans = ""; TextAnnotation ta = taBuilder.createTextAnnotation(text); List<QuantSpan> quantSpans = getSpans(text, standardized, null); int quantIndex = 0; for (int i = 0; i < ta.size(); ++i) { if (quantSpans.get(quantIndex).start == ta.getTokenCharacterOffset(i).getFirst()) { ans += " [ "; } ans += ta.getToken(i) + " "; if (quantSpans.get(quantIndex).end == ta.getTokenCharacterOffset(i).getSecond()) { ans += " ] " + quantSpans.get(quantIndex) + " "; if (quantIndex < quantSpans.size() - 1) quantIndex++; } } return ans; }
if(start == -1) start = i; end = i; int first = ta.getTokenCharacterOffset(i).getFirst(); int second = ta.getTokenCharacterOffset(i).getSecond(); if(firstCharOffset == -1) firstCharOffset = first; tokensPairs.add(new IntPair(first - firstCharOffset, second - firstCharOffset)); // apply the char offsets
if(start == -1) start = i; end = i; int first = ta.getTokenCharacterOffset(i).getFirst(); int second = ta.getTokenCharacterOffset(i).getSecond(); if(firstCharOffset == -1) firstCharOffset = first; tokensPairs.add(new IntPair(first - firstCharOffset, second - firstCharOffset)); // apply the char offsets
1.0 * (tens.get(ta.getToken(i).toLowerCase()) + units .get(ta.getToken(i + 1).toLowerCase())), ""), ta .getTokenCharacterOffset(i).getFirst(), ta .getTokenCharacterOffset(i + 1).getSecond()); qsList.add(qs); i++; QuantSpan qs = new QuantSpan(new Quantity("=", 1.0 * numberWords.get(ta.getToken(i) .toLowerCase()), ""), ta.getTokenCharacterOffset(i).getFirst(), ta .getTokenCharacterOffset(i).getSecond()); qsList.add(qs);
1.0 * (tens.get(ta.getToken(i).toLowerCase()) + units .get(ta.getToken(i + 1).toLowerCase())), ""), ta .getTokenCharacterOffset(i).getFirst(), ta .getTokenCharacterOffset(i + 1).getSecond()); qsList.add(qs); i++; QuantSpan qs = new QuantSpan(new Quantity("=", 1.0 * numberWords.get(ta.getToken(i) .toLowerCase()), ""), ta.getTokenCharacterOffset(i).getFirst(), ta .getTokenCharacterOffset(i).getSecond()); qsList.add(qs);
} else { if (startSpan >= 0) { startCharOffset = text.getTokenCharacterOffset(startSpan).getFirst(); } else startCharOffset = -1; endCharOffset = text.getTokenCharacterOffset(endSpan - 1).getSecond(); else endCharOffset = text.getTokenCharacterOffset(endSpan).getSecond(); } else endCharOffset = 0;
} else { if (startSpan >= 0) { startCharOffset = text.getTokenCharacterOffset(startSpan).getFirst(); } else startCharOffset = -1; endCharOffset = text.getTokenCharacterOffset(endSpan - 1).getSecond(); else endCharOffset = text.getTokenCharacterOffset(endSpan).getSecond(); } else endCharOffset = 0;
if (!inChunk && tokenPos < annotation.size()) { inChunk = true; startPos = annotation.getTokenCharacterOffset(tokenPos).getFirst(); .discreteValue(tokens.get(i + 1)).endsWith(prediction.substring(2)))) { endPos = annotation.getTokenCharacterOffset(tokenPos).getSecond() - 1; QuantSpan span = new QuantSpan(null, startPos, endPos); try {
if (!inChunk && tokenPos < annotation.size()) { inChunk = true; startPos = annotation.getTokenCharacterOffset(tokenPos).getFirst(); .discreteValue(tokens.get(i + 1)).endsWith(prediction.substring(2)))) { endPos = annotation.getTokenCharacterOffset(tokenPos).getSecond() - 1; QuantSpan span = new QuantSpan(null, startPos, endPos); try {
charStart = ta.getTokenCharacterOffset(currSpan.getFirst()).getFirst(); charEnd = ta.getTokenCharacterOffset(currSpan.getFirst()).getSecond()-5; charStart = ta.getTokenCharacterOffset(currSpan.getFirst()).getFirst()+5; charEnd = ta.getTokenCharacterOffset(currSpan.getFirst()).getSecond(); int searchStart = ta.getTokenCharacterOffset(match.getFirst()).getFirst(); if (searchStart>currPos) { currSpan = match;
charStart = ta.getTokenCharacterOffset(currSpan.getFirst()).getFirst(); charEnd = ta.getTokenCharacterOffset(currSpan.getFirst()).getSecond()-5; charStart = ta.getTokenCharacterOffset(currSpan.getFirst()).getFirst()+5; charEnd = ta.getTokenCharacterOffset(currSpan.getFirst()).getSecond(); int searchStart = ta.getTokenCharacterOffset(match.getFirst()).getFirst(); if (searchStart>currPos) { currSpan = match;