tanl: tanl: tag/SST/SST.h Source File

00001 /*
00002 **  Tanl
00003 **  SST/SST.h
00004 **  ----------------------------------------------------------------------
00005 **  Copyright (c) 2005  Giuseppe Attardi (attardi@di.unipi.it).
00006 **  ----------------------------------------------------------------------
00007 **
00008 **  This file is part of Tanl.
00009 **
00010 **  Tanl is free software; you can redistribute it and/or modify it
00011 **  under the terms of the GNU General Public License, version 3,
00012 **  as published by the Free Software Foundation.
00013 **
00014 **  Tanl is distributed in the hope that it will be useful,
00015 **  but WITHOUT ANY WARRANTY; without even the implied warranty of
00016 **  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
00017 **  GNU General Public License for more details.
00018 **
00019 **  You should have received a copy of the GNU General Public License
00020 **  along with this program.  If not, see <http://www.gnu.org/licenses/>.
00021 **  ----------------------------------------------------------------------
00022 */
00023 
00024 #ifndef Tanl_SST_SST_H
00025 #define Tanl_SST_SST_H
00026 
00027 // IXE library
00028 #include "conf/conf_bool.h"
00029 #include "conf/conf_float.h"
00030 #include "conf/conf_int.h"
00031 #include "conf/conf_string.h"
00032 
00033 // local
00034 #include "SstEventStream.h"
00035 #include "include/IPipe.h"
00036 #include "Corpus/Corpus.h"
00037 #include "classifier/MaxEnt.h"
00038 
00039 namespace Tanl {
00040 namespace SST {
00041 
00046 
00047 // Configuration Parameters
00049 
00051 extern IXE::conf<std::string>   resourceDir;
00053 extern IXE::conf<std::string>   language;
00055 extern IXE::conf<int>   cutoff;
00057 extern IXE::conf<int>   iter;
00059 extern IXE::conf<float> alpha;
00061 extern IXE::conf<bool>  verbose;
00063 //extern IXE::conf<bool>        oldIOB;
00065 //extern IXE::conf<bool>        refine;
00066 
00070 class SST : public IPipe<std::vector<Token*>*, std::vector<Token*>*>
00071 {
00072 public:
00073 
00078   SST(char const* modelFile, char const* configFile = 0);
00079 
00080   ~SST();
00081 
00086   void          train(SentenceReader* sentenceReader, char const* modelFile);
00087 
00088   Enumerator<std::vector<Token*>*>*     pipe(Enumerator<std::vector<Token*>*>& sen);
00089 
00090   friend class SSTPipe;
00091 
00092  private:
00093   Classifier::MaxEnt*   model;
00094   Resources             resources;
00095 };
00096 
00100 struct SSTPipe : public Enumerator<std::vector<Token*>*>
00101 {
00103   SSTPipe(SST& sst, Enumerator<std::vector<Token*>*>& se);
00104 
00107   bool                  MoveNext();
00108 
00110   std::vector<Token*>*  Current();
00111   
00112   private:
00113   SST&                                  sst;
00114   Enumerator<std::vector<Token*>*>&     se;
00115   SstEventStream                        eventStream;
00116   unordered_map<int, int>               outcomeId;
00117 };
00118 
00119 } // namespace SST
00120 } // namespace Tanl
00121 
00122 #endif // Tanl_SST_SST_H