PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // LemmatizeVMatrix.h 00004 // 00005 // Copyright (C) 2005 Hugo Larochelle 00006 // 00007 // Redistribution and use in source and binary forms, with or without 00008 // modification, are permitted provided that the following conditions are met: 00009 // 00010 // 1. Redistributions of source code must retain the above copyright 00011 // notice, this list of conditions and the following disclaimer. 00012 // 00013 // 2. Redistributions in binary form must reproduce the above copyright 00014 // notice, this list of conditions and the following disclaimer in the 00015 // documentation and/or other materials provided with the distribution. 00016 // 00017 // 3. The name of the authors may not be used to endorse or promote 00018 // products derived from this software without specific prior written 00019 // permission. 00020 // 00021 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR 00022 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES 00023 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN 00024 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 00025 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED 00026 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 00027 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 00028 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 00029 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 00030 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 00031 // 00032 // This file is part of the PLearn library. For more information on the PLearn 00033 // library, go to the PLearn Web site at www.plearn.org 00034 00035 /* ******************************************************* 00036 * $Id: .pyskeleton_header 544 2003-09-01 00:05:31Z plearner $ 00037 ******************************************************* */ 00038 00039 // Authors: Hugo Larochelle 00040 00044 #ifndef LemmatizeVMatrix_INC 00045 #define LemmatizeVMatrix_INC 00046 00047 #include <plearn/vmat/SourceVMatrix.h> 00048 #include <plearn/dict/Dictionary.h> 00049 #include <plearn/dict/WordNetSenseDictionary.h> 00050 00051 namespace PLearn { 00052 00062 class LemmatizeVMatrix : public SourceVMatrix 00063 { 00064 typedef SourceVMatrix inherited; 00065 00066 public: 00068 int word_field; 00070 int pos_field; 00073 TMat<string> pos_to_lemma_table; 00076 TMat<string> word_to_lemma_table; 00079 TMat<string> word_pos_to_lemma_table; 00080 00081 public: 00083 LemmatizeVMatrix(); 00084 00085 PLEARN_DECLARE_OBJECT(LemmatizeVMatrix); 00086 00087 // Simply calls inherited::build() then build_() 00088 virtual void build(); 00089 00091 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00092 00094 virtual real getStringVal(int col, const string & str) const; 00095 00096 virtual string getValString(int col, real val) const; 00097 00098 virtual void getValues(int row, int col, Vec& values) const; 00099 00101 virtual void getValues(const Vec& input, int col, Vec& values) const; 00102 00104 virtual PP<Dictionary> getDictionary(int col) const; 00105 00106 00107 protected: 00109 PP<Dictionary> lemma_dict; 00111 Vec src_row; 00112 00113 protected: 00115 static void declareOptions(OptionList& ol); 00116 00119 virtual void getNewRow(int i, const Vec& v) const; 00120 00121 private: 00122 //##### Private Member Functions ######################################## 00123 00125 void build_(); 00126 00128 string getLemma(int row) const; 00129 00130 private: 00131 }; 00132 00133 // Declares a few other classes and functions related to this class 00134 DECLARE_OBJECT_PTR(LemmatizeVMatrix); 00135 00136 } // end of namespace PLearn 00137 00138 #endif 00139 00140 00141 /* 00142 Local Variables: 00143 mode:c++ 00144 c-basic-offset:4 00145 c-file-style:"stroustrup" 00146 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00147 indent-tabs-mode:nil 00148 fill-column:79 00149 End: 00150 */ 00151 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :