mirror of
https://github.com/moses-smt/mosesdecoder.git
synced 2025-01-08 12:36:35 +03:00
580acce9e2
programs: `extract' for the phrase-based model and `extract-rules' for tree-based models. They could be combined into a single program, but they're probably sufficiently different that it isn't worthwhile. git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@3129 1f5c12ca-751b-0410-a591-d2e778427230
80 lines
2.6 KiB
C++
80 lines
2.6 KiB
C++
/***********************************************************************
|
|
Moses - factored phrase-based language decoder
|
|
Copyright (C) 2010 University of Edinburgh
|
|
|
|
This library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
This library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with this library; if not, write to the Free Software
|
|
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
***********************************************************************/
|
|
|
|
#pragma once
|
|
#ifndef RULEEXTRACTIONOPTIONS_H_INCLUDED_
|
|
#define RULEEXTRACTIONOPTIONS_H_INCLUDED_
|
|
|
|
struct RuleExtractionOptions
|
|
{
|
|
public:
|
|
int maxSpan;
|
|
int minHoleSource;
|
|
int minHoleTarget;
|
|
int minWords;
|
|
int maxSymbolsTarget;
|
|
int maxSymbolsSource;
|
|
bool onlyDirectFlag;
|
|
bool glueGrammarFlag;
|
|
bool unknownWordLabelFlag;
|
|
bool onlyOutputSpanInfo;
|
|
bool noFileLimit;
|
|
bool properConditioning;
|
|
int maxNonTerm;
|
|
bool nonTermFirstWord;
|
|
bool nonTermConsecTarget;
|
|
bool nonTermConsecSource;
|
|
bool requireAlignedWord;
|
|
bool sourceSyntax;
|
|
bool targetSyntax;
|
|
bool duplicateRules;
|
|
bool fractionalCounting;
|
|
bool mixed;
|
|
|
|
RuleExtractionOptions()
|
|
: maxSpan(10)
|
|
, minHoleSource(2)
|
|
, minHoleTarget(1)
|
|
, minWords(1)
|
|
, maxSymbolsTarget(999)
|
|
, maxSymbolsSource(5)
|
|
// int minHoleSize(1)
|
|
// int minSubPhraseSize(1) // minimum size of a remaining lexical phrase
|
|
, onlyDirectFlag(false)
|
|
, glueGrammarFlag(false)
|
|
, unknownWordLabelFlag(false)
|
|
, onlyOutputSpanInfo(false)
|
|
, noFileLimit(false)
|
|
//bool zipFiles(false)
|
|
, properConditioning(false)
|
|
, maxNonTerm(2)
|
|
, nonTermFirstWord(true)
|
|
, nonTermConsecTarget(true)
|
|
, nonTermConsecSource(false)
|
|
, requireAlignedWord(true)
|
|
, sourceSyntax(false)
|
|
, targetSyntax(false)
|
|
, duplicateRules(true)
|
|
, fractionalCounting(true)
|
|
, mixed(false)
|
|
{}
|
|
};
|
|
|
|
#endif
|