The following is excerpted from a tutorial I'm putting together for a class. (NB: This assumes you have successfully installed GIZA++-v2 on a *nix system.)
Start with two data files containing parallel sentences that have been tokenized, one sentence per line. For example, a pair of parallel English-French files might read as follows.
Sample 1 - train.en
I gave him the book .
He read the book .
He loved the book .
Sample 2 - train.fr
Je lui ai donne/ le livre .
Il a lu le livre .
Il aimait le livre .
Run these files through plain2snt.out to get target and source vocabulary files (*.vcb) as well as a sentence pair file (*.snt).
From the GIZA++ directory, run:
./plain2snt.out TEXT1 TEXT2
where TEXT1 and TEXT2 are the data files described in step 1.
This produces four files in the same directory as TEXT1 and TEXT2 (assuming they are in the same directory):
TEXT1_TEXT2.snt
TEXT1.vcb
TEXT2_TEXT1.snt
TEXT2.vcb
The vocab files contain a unique (integer) ID for each word in the text (NB: not tokenized/lemmatized), the word/string, and the number of times that string occurred. These are separated by a single space character.
The sentence files contain numbers. For each sentence pair, there are three lines: the first is a count of the number of times that sentence pair occurs in the corpus and the second and third are a string of (space-separated) numbers corresponding to the entries for words in the vocab files. Based on the naming convention for *.snt files, the first file is assumed to be the source, and the second is assumed to be the target language. For example, in the file TEXT1_TEXT2.snt, the first line will be a count of the number of times the first sentence-pair occurred in the corpus, the second line will be a string of numbers corresponding to words in the TEXT1.vcb file, and the third line will be a string of numbers corresponding to words in the TEXT2.vcb file.
Now TEXT1.vcb, TEXT2.vcb, and either of the two *.snt files can be used as input to GIZA++ to produce an alignment.
But note that when I tried to run this, I had to rename TEXT1_TEXT2.snt to something without an underscore in the name in order to get any proper output.
发布评论
评论（5）
以下内容摘自我为课程编写的教程。 （注意：这假设您已在 *nix 系统上成功安装 GIZA++-v2。）
示例 1 -
train.en示例 2 -
train.frplain2snt.out运行这些文件以获取目标和源词汇文件 (*.vcb）以及句子对文件（*.snt）。从 GIZA++ 目录中，运行：
其中
TEXT1和TEXT2是步骤 1 中描述的数据文件。这会在与
TEXT1相同的目录中生成四个文件> 和TEXT2（假设它们位于同一目录中）：词汇文件包含文本中每个单词的唯一（整数）ID（注意：未标记化/词形还原）、单词/字符串以及该字符串出现的次数。它们由单个空格字符分隔。
句子文件包含数字。对于每个句子对，有三行：第一行是该句子对在语料库中出现的次数的计数，第二行和第三行是对应于语料库中单词条目的一串（以空格分隔的）数字。词汇文件。根据
*.snt文件的命名约定，第一个文件被假定为源语言，第二个文件被假定为目标语言。例如，在文件TEXT1_TEXT2.snt中，第一行将是第一个句子对在语料库中出现的次数，第二行将是对应于的一串数字TEXT1.vcb文件中的单词，第三行是与TEXT2.vcb文件中的单词对应的数字字符串。TEXT1.vcb、TEXT2.vcb和两个*.snt文件中的任何一个都可以用作 GIZA++ 的输入来生成比对。例如：
但请注意，当我尝试运行此程序时，我必须将
TEXT1_TEXT2.snt重命名为名称中不带下划线的名称，才能获得正确的输出。The following is excerpted from a tutorial I'm putting together for a class. (NB: This assumes you have successfully installed GIZA++-v2 on a *nix system.)
Sample 1 -
train.enSample 2 -
train.frplain2snt.outto get target and source vocabulary files (*.vcb) as well as a sentence pair file (*.snt).From the GIZA++ directory, run:
where
TEXT1andTEXT2are the data files described in step 1.This produces four files in the same directory as
TEXT1andTEXT2(assuming they are in the same directory):The vocab files contain a unique (integer) ID for each word in the text (NB: not tokenized/lemmatized), the word/string, and the number of times that string occurred. These are separated by a single space character.
The sentence files contain numbers. For each sentence pair, there are three lines: the first is a count of the number of times that sentence pair occurs in the corpus and the second and third are a string of (space-separated) numbers corresponding to the entries for words in the vocab files. Based on the naming convention for
*.sntfiles, the first file is assumed to be the source, and the second is assumed to be the target language. For example, in the fileTEXT1_TEXT2.snt, the first line will be a count of the number of times the first sentence-pair occurred in the corpus, the second line will be a string of numbers corresponding to words in theTEXT1.vcbfile, and the third line will be a string of numbers corresponding to words in theTEXT2.vcbfile.TEXT1.vcb,TEXT2.vcb, and either of the two*.sntfiles can be used as input to GIZA++ to produce an alignment.For example:
But note that when I tried to run this, I had to rename
TEXT1_TEXT2.sntto something without an underscore in the name in order to get any proper output.这个Powerpoint教程对我有用：http://www.tc.umn.edu /~bthomson/wordalignment/GIZA.ppt
This Powerpoint tutorial worked for me: http://www.tc.umn.edu/~bthomson/wordalignment/GIZA.ppt
这非常有帮助：
http://fabioticconi.wordpress.com/2011/01/17/how-to-do-a-word-alignment-with-giza-or-mgiza-from-parallel-corpus/
IIT-B 学者为 GIZA++ 和 MOSES 设置和使用提供了精彩而详细的演示。
其中一些是：
http://www. cse.iitb.ac.in/~pb/cs712-2013/potpouri/kashyap-giza-mozes-jan2013.pdf
http://www.cse.iitb.ac.in/~anoopk/publications/presentations/moses_giza_intro.pdf
http://www.cfilt.iitb.ac.in/Moses-Tutorial.pdf
This one is very helpful :
http://fabioticconi.wordpress.com/2011/01/17/how-to-do-a-word-alignment-with-giza-or-mgiza-from-parallel-corpus/
IIT-B scholars have put up nice and detailed presentations for GIZA++ and MOSES setup and use.
Some of them are :
http://www.cse.iitb.ac.in/~pb/cs712-2013/potpouri/kashyap-giza-mozes-jan2013.pdf
http://www.cse.iitb.ac.in/~anoopk/publications/presentations/moses_giza_intro.pdf
http://www.cfilt.iitb.ac.in/Moses-Tutorial.pdf
也许是这个？
http ://code.google.com/p/giza-pp/issues/attachmentText?id=8&aid=697742396599277757&name=README-rst&token=40fba3d449abc12366b98b04cfe7dbc1
完整来源：http://code.google.com/p/giza-pp/issues/detail?id= 8
This one maybe ?
http://code.google.com/p/giza-pp/issues/attachmentText?id=8&aid=697742396599277757&name=README-rst&token=40fba3d449abc12366b98b04cfe7dbc1
Full source : http://code.google.com/p/giza-pp/issues/detail?id=8
这里有关于如何格式化输入文件以及如何运行 GIZA++ 的补充说明：
http://www.tc.umn.edu/~bthomson/wordalignment/GIZAREADME.txt
There is a supplemental explanation of how to format input files and how to run GIZA++ over here:
http://www.tc.umn.edu/~bthomson/wordalignment/GIZAREADME.txt