PLearn 0.1
WordNetSenseDictionary.h
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // WordNetSenseDictionary.h
00004 //
00005 // Copyright (C) 2004 Hugo Larochelle Christopher Kermorvant
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: WordNetSenseDictionary.h 6338 2006-10-23 20:33:09Z larocheh $ 
00037  ******************************************************* */
00038 
00039 // Authors: Hugo Larochelle, Christopher Kermorvant
00040 
00044 #ifndef WordNetSenseDictionary_INC
00045 #define WordNetSenseDictionary_INC
00046 #include "Dictionary.h"
00047 #include "wn.h"
00048 
00049 #define WN_ROOT_NODE "wn_root_node"
00050 #define WN_NOUN_NODE "wn_noun_node"
00051 #define WN_VERB_NODE "wn_verb_node"
00052 #define WN_ADJ_NODE "wn_adj_node"
00053 #define WN_ADV_NODE "wn_adv_node"
00054 
00055 namespace PLearn {
00056 using namespace std;
00057 
00058 // Tool functions
00059 
00063 char* cstr(string& str);
00065 string getSynsetKey(SynsetPtr ssp);
00067 SynsetPtr getSynsetPtr(string synset_key);
00071 void extractSenses(string word, int wn_pos, string symbol_type, TVec<string>& senses,TVec<int>& tagcnts, TVec< TVec<string> >& ancestors, bool extract_ancestors=false);
00073 void extractAncestors(TVec<SynsetPtr> anc, TVec< TVec<string> >& anc_str, string root_node=WN_ROOT_NODE);
00075 string stemWord(string word);
00077 string stemWord(string word, int wn_pos);
00079 void stemsOfWord(string word, int wn_pos, TVec<string>& stems);
00081 void stemsOfWord(string word, TVec<string>& stems);
00082 
00087 class WordNetSenseDictionary: public Dictionary
00088 {
00089 
00090 private:
00091   
00092     typedef Dictionary inherited;
00093 
00094 protected:
00095 
00097     Vec possible_values;
00098 
00099 public:
00100 
00101     // ************************
00102     // * public build options *
00103     // ************************
00104 
00106     bool options_stem_words;
00107     
00109     bool options_to_lower_case;
00110 
00112     string symbol_type;
00113 
00115     hash_map<string,Vec > possible_values_for_word;
00116 
00117     // Hierarchy information:
00118 
00120     bool use_wordnet_hierarchy;
00121 
00123     hash_map<int, TVec<int> > children;
00124 
00126     hash_map<int, TVec<int> > parents;
00127 
00129     hash_map<string, real> sense_prior;
00130 
00131 protected:
00132 
00134     TVec<string> stems;
00135     
00137     TVec<string> senses;
00138 
00140     TVec< TVec<string> > ancestors_vec;
00141 
00143     TVec<int> tagcnts;
00144 
00146     int ret;
00147 
00149     string word_sense;
00150 
00151 
00152     // ******************
00153     // * Object methods *
00154     // ******************
00155 
00156 private: 
00158     void build_();
00159 
00160 protected: 
00162     static void declareOptions(OptionList& ol);
00163 
00164     void getSensesFromWordNet(TVec<string> options);
00165 
00166 public:
00167 
00168     // ****************
00169     // * Constructors *
00170     // ****************
00171 
00173     WordNetSenseDictionary();
00174 
00175     // Declares other standard object methods.
00176     PLEARN_DECLARE_OBJECT(WordNetSenseDictionary);
00177 
00178     virtual int getId(string symbol, TVec<string> options = TVec<string>(0));
00179 
00180     virtual void getValues(TVec<string> options, Vec& values);
00181     
00182     virtual int size(TVec<string> options=TVec<string>(0));
00183 
00187     virtual void parentsOf(int sense, TVec<int>& the_parents);
00188 
00192     virtual void childrenOf(int sense, TVec<int>& the_children);
00193 
00195     virtual int rootNode();
00196 
00198     virtual real sensePrior(string word, string sense);
00199 
00200     // simply calls inherited::build() then build_() 
00201     virtual void build();
00202 
00204     virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies);
00205 
00206 };
00207 
00208 // Declares a few other classes and functions related to this class
00209 DECLARE_OBJECT_PTR(WordNetSenseDictionary);
00210   
00211 } // end of namespace PLearn
00212 
00213 #endif
00214 
00215 
00216 /*
00217   Local Variables:
00218   mode:c++
00219   c-basic-offset:4
00220   c-file-style:"stroustrup"
00221   c-file-offsets:((innamespace . 0)(inline-open . 0))
00222   indent-tabs-mode:nil
00223   fill-column:79
00224   End:
00225 */
00226 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines