tanl: tanl: tag/Tanlpos/HMM.h Source File

00001 /*
00002 **  Tanl
00003 **  tag/TanlPos/HMM.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_POS_HMM_H
00025 #define Tanl_POS_HMM_H
00026 
00027 // standard
00028 #include <string>
00029 
00030 // local
00031 #include "State.h"
00032 
00033 namespace Tanl { namespace POS {
00034     
00038 struct HMM {
00044   typedef std::pair<State, double> Transition;
00045     
00046   enum seen_type { Seen, LowerCaseSeen, SpecialToken, UnSeen };
00047 
00048   struct Observation {
00049         
00050     Observation() { }
00051 
00052     Observation(std::string& word) :
00053       word(word), is_first(false), seen(Seen) { }
00054         
00055     char const* type2string() const {
00056       switch (seen) {
00057       case Seen: return "S";
00058       case LowerCaseSeen: return "*L";
00059       case SpecialToken: return "*D";
00060       case UnSeen: return "*";
00061       }
00062     }
00063         
00064     std::string word;
00065     bool is_first; /* ugly hack, to compute h in the first word */
00066     seen_type seen; 
00067     std::vector<std::string> anals;
00068     std::vector<std::pair<std::string, double> > guessed;
00069   };
00070     
00075   virtual std::vector<Transition> transitions(State const& from,
00076                                               Observation const& obs) { }
00077 
00078   typedef std::vector<Observation> Observations;
00079 };
00080 
00081 } // namespace POS
00082 } // namespace Tanl
00083 
00084 #endif // Tanl_POS_HMM_H