/// <summary> /// Generate a <see cref="BiSegGraph"/> based upon a <see cref="SegGraph"/> /// </summary> private void GenerateBiSegGraph(SegGraph segGraph) { double smooth = 0.1; int wordPairFreq = 0; int maxStart = segGraph.MaxStart; double oneWordFreq, weight, tinyDouble = 1.0 / Utility.MAX_FREQUENCE; int next; char[] idBuffer; // get the list of tokens ordered and indexed segTokenList = segGraph.MakeIndex(); // Because the beginning position of startToken is -1, therefore startToken can be obtained when key = -1 int key = -1; IList <SegToken> nextTokens = null; while (key < maxStart) { if (segGraph.IsStartExist(key)) { IList <SegToken> tokenList = segGraph.GetStartList(key); // Calculate all tokens for a given key. foreach (SegToken t1 in tokenList) { oneWordFreq = t1.Weight; next = t1.EndOffset; nextTokens = null; // Find the next corresponding Token. // For example: "Sunny seashore", the present Token is "sunny", next one should be "sea" or "seashore". // If we cannot find the next Token, then go to the end and repeat the same cycle. while (next <= maxStart) { // Because the beginning position of endToken is sentenceLen, so equal to sentenceLen can find endToken. if (segGraph.IsStartExist(next)) { nextTokens = segGraph.GetStartList(next); break; } next++; } if (nextTokens == null) { break; } foreach (SegToken t2 in nextTokens) { idBuffer = new char[t1.CharArray.Length + t2.CharArray.Length + 1]; System.Array.Copy(t1.CharArray, 0, idBuffer, 0, t1.CharArray.Length); idBuffer[t1.CharArray.Length] = BigramDictionary.WORD_SEGMENT_CHAR; System.Array.Copy(t2.CharArray, 0, idBuffer, t1.CharArray.Length + 1, t2.CharArray.Length); // Two linked Words frequency wordPairFreq = bigramDict.GetFrequency(idBuffer); // Smoothing // -log{a*P(Ci-1)+(1-a)P(Ci|Ci-1)} Note 0<a<1 weight = -Math .Log(smooth * (1.0 + oneWordFreq) / (Utility.MAX_FREQUENCE + 0.0) + (1.0 - smooth) * ((1.0 - tinyDouble) * wordPairFreq / (1.0 + oneWordFreq) + tinyDouble)); SegTokenPair tokenPair = new SegTokenPair(idBuffer, t1.Index, t2.Index, weight); this.AddSegTokenPair(tokenPair); } } } key++; } }
/// <summary> /// Create the <see cref="SegGraph"/> for a sentence. /// </summary> /// <param name="sentence">input sentence, without start and end markers</param> /// <returns><see cref="SegGraph"/> corresponding to the input sentence.</returns> private SegGraph CreateSegGraph(string sentence) { int i = 0, j; int length = sentence.Length; int foundIndex; CharType[] charTypeArray = GetCharTypes(sentence); StringBuilder wordBuf = new StringBuilder(); SegToken token; int frequency = 0; // the number of times word appears. bool hasFullWidth; WordType wordType; char[] charArray; SegGraph segGraph = new SegGraph(); while (i < length) { hasFullWidth = false; switch (charTypeArray[i]) { case CharType.SPACE_LIKE: i++; break; case CharType.HANZI: j = i + 1; //wordBuf.delete(0, wordBuf.length()); wordBuf.Remove(0, wordBuf.Length); // It doesn't matter if a single Chinese character (Hanzi) can form a phrase or not, // it will store that single Chinese character (Hanzi) in the SegGraph. Otherwise, it will // cause word division. wordBuf.Append(sentence[i]); charArray = new char[] { sentence[i] }; frequency = wordDict.GetFrequency(charArray); token = new SegToken(charArray, i, j, WordType.CHINESE_WORD, frequency); segGraph.AddToken(token); foundIndex = wordDict.GetPrefixMatch(charArray); while (j <= length && foundIndex != -1) { if (wordDict.IsEqual(charArray, foundIndex) && charArray.Length > 1) { // It is the phrase we are looking for; In other words, we have found a phrase SegToken // from i to j. It is not a monosyllabic word (single word). frequency = wordDict.GetFrequency(charArray); token = new SegToken(charArray, i, j, WordType.CHINESE_WORD, frequency); segGraph.AddToken(token); } while (j < length && charTypeArray[j] == CharType.SPACE_LIKE) { j++; } if (j < length && charTypeArray[j] == CharType.HANZI) { wordBuf.Append(sentence[j]); charArray = new char[wordBuf.Length]; //wordBuf.GetChars(0, charArray.Length, charArray, 0); wordBuf.CopyTo(0, charArray, 0, charArray.Length); // idArray has been found (foundWordIndex!=-1) as a prefix before. // Therefore, idArray after it has been lengthened can only appear after foundWordIndex. // So start searching after foundWordIndex. foundIndex = wordDict.GetPrefixMatch(charArray, foundIndex); j++; } else { break; } } i++; break; case CharType.FULLWIDTH_LETTER: hasFullWidth = true; /* intentional fallthrough */ j = i + 1; while (j < length && (charTypeArray[j] == CharType.LETTER || charTypeArray[j] == CharType.FULLWIDTH_LETTER)) { if (charTypeArray[j] == CharType.FULLWIDTH_LETTER) { hasFullWidth = true; } j++; } // Found a Token from i to j. Type is LETTER char string. charArray = Utility.STRING_CHAR_ARRAY; frequency = wordDict.GetFrequency(charArray); wordType = hasFullWidth ? WordType.FULLWIDTH_STRING : WordType.STRING; token = new SegToken(charArray, i, j, wordType, frequency); segGraph.AddToken(token); i = j; break; case CharType.LETTER: j = i + 1; while (j < length && (charTypeArray[j] == CharType.LETTER || charTypeArray[j] == CharType.FULLWIDTH_LETTER)) { if (charTypeArray[j] == CharType.FULLWIDTH_LETTER) { hasFullWidth = true; } j++; } // Found a Token from i to j. Type is LETTER char string. charArray = Utility.STRING_CHAR_ARRAY; frequency = wordDict.GetFrequency(charArray); wordType = hasFullWidth ? WordType.FULLWIDTH_STRING : WordType.STRING; token = new SegToken(charArray, i, j, wordType, frequency); segGraph.AddToken(token); i = j; break; case CharType.FULLWIDTH_DIGIT: hasFullWidth = true; /* intentional fallthrough */ j = i + 1; while (j < length && (charTypeArray[j] == CharType.DIGIT || charTypeArray[j] == CharType.FULLWIDTH_DIGIT)) { if (charTypeArray[j] == CharType.FULLWIDTH_DIGIT) { hasFullWidth = true; } j++; } // Found a Token from i to j. Type is NUMBER char string. charArray = Utility.NUMBER_CHAR_ARRAY; frequency = wordDict.GetFrequency(charArray); wordType = hasFullWidth ? WordType.FULLWIDTH_NUMBER : WordType.NUMBER; token = new SegToken(charArray, i, j, wordType, frequency); segGraph.AddToken(token); i = j; break; case CharType.DIGIT: j = i + 1; while (j < length && (charTypeArray[j] == CharType.DIGIT || charTypeArray[j] == CharType.FULLWIDTH_DIGIT)) { if (charTypeArray[j] == CharType.FULLWIDTH_DIGIT) { hasFullWidth = true; } j++; } // Found a Token from i to j. Type is NUMBER char string. charArray = Utility.NUMBER_CHAR_ARRAY; frequency = wordDict.GetFrequency(charArray); wordType = hasFullWidth ? WordType.FULLWIDTH_NUMBER : WordType.NUMBER; token = new SegToken(charArray, i, j, wordType, frequency); segGraph.AddToken(token); i = j; break; case CharType.DELIMITER: j = i + 1; // No need to search the weight for the punctuation. Picking the highest frequency will work. frequency = Utility.MAX_FREQUENCE; charArray = new char[] { sentence[i] }; token = new SegToken(charArray, i, j, WordType.DELIMITER, frequency); segGraph.AddToken(token); i = j; break; default: j = i + 1; // Treat the unrecognized char symbol as unknown string. // For example, any symbol not in GB2312 is treated as one of these. charArray = Utility.STRING_CHAR_ARRAY; frequency = wordDict.GetFrequency(charArray); token = new SegToken(charArray, i, j, WordType.STRING, frequency); segGraph.AddToken(token); i = j; break; } } // Add two more Tokens: "beginning xx beginning" charArray = Utility.START_CHAR_ARRAY; frequency = wordDict.GetFrequency(charArray); token = new SegToken(charArray, -1, 0, WordType.SENTENCE_BEGIN, frequency); segGraph.AddToken(token); // "end xx end" charArray = Utility.END_CHAR_ARRAY; frequency = wordDict.GetFrequency(charArray); token = new SegToken(charArray, length, length + 1, WordType.SENTENCE_END, frequency); segGraph.AddToken(token); return(segGraph); }
public BiSegGraph(SegGraph segGraph) { segTokenList = segGraph.MakeIndex(); GenerateBiSegGraph(segGraph); }