tag/Tanlpos/lexicon.h
00001 /* 00002 ** Tanl 00003 ** tag/TanlPos/lexicon.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_lexicon_H 00025 #define Tanl_POS_lexicon_H 00026 00027 #include "Tag.h" 00028 00029 // standard 00030 #include <map> 00031 #include <vector> 00032 00033 namespace Tanl { namespace POS { 00034 00035 typedef std::vector<std::pair<TagID, int> > TagFreq; 00036 00045 struct Lexicon : public std::map<std::string, TagFreq> 00046 { 00047 void add(std::string& word, TagID tag); 00048 00049 //void add_word_tag(std::string& word, TagID tag); 00050 std::vector<TagID>* find_nofreq(std::string& w); 00051 00052 void serialize(std::ostream &); 00053 void serialize(std::istream &); 00054 }; 00055 00056 } // namespace POS 00057 } // namespace Tanl 00058 00059 #endif // Tanl_POS_lexicon_H