Sophie

Sophie

distrib > Mandriva > 2010.0 > i586 > media > contrib-release > by-pkgid > 1dcef8f7b86dc3b3c7b89dd968fc4c12 > files > 21

mecab-0.96-1mdv2008.1.i586.rpm

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=EUC-JP">
<title>MeCab: Yet Another Japanese Dependency Structure
Analyzer</title>
<link type="text/css" rel="stylesheet" href="mecab.css">
</head>
<body>
<h1>½ÐÎÏ¥Õ¥©¡¼¥Þ¥Ã¥È</h1>

<p>$Id: format.html 65 2007-01-30 00:52:53Z taku-ku $;</p>

<h2>³µÍ×</h2>
<p>MeCab ¤Ï, ChaSen ¤ÈƱÍÍ,
½ÐÎϤΥե©¡¼¥Þ¥Ã¥È¤òÈæ³ÓŪ¼«Í³¤ËºÆÄêµÁ¤¹¤ë¤³¤È¤¬¤Ç¤­¤Þ¤¹.
¤Þ¤¿, ÀßÄê¥Õ¥¡¥¤¥ë¤Ë¥Õ¥©¡¼¥Þ¥Ã¥È¤òÊ£¿ôµ­½Ò¤·¤Æ¤ª¤­,
¼Â¹Ô»þ¤Ë¤½¤ì¤é¤ò ÀÚ¤êÊѤ¨¤ë¤³¤È¤¬²Äǽ¤Ç¤¹.
¤³¤ì¤Ï, MeCab Æȼ«¤Îµ¡Ç½¤Ç¤¹.</p>

<h2>½ÐÎÏ¥Õ¥©¡¼¥Þ¥Ã¥È¤Î»ØÄê</h2>

<p>°Ê²¼¤Î
3¤Ä½ÐÎÏ¥Õ¥©¡¼¥Þ¥Ã¥È¤òÊѹ¹¤¹¤ë¤³¤È¤¬¤Ç¤­¤Þ¤¹.</p>

<ul>
<li>node: 1¤Ä¤Î·ÁÂÖÁǤò½ÐÎÏ, ¥Ç¥Õ¥©¥ë¥È¤Ï¶õʸ»ú</li>

<li>unk:  1¤Ä¤Î̤Ãθì·ÁÂÖÁǤò½ÐÎÏ, ¥Ç¥Õ¥©¥ë¥È¤Ï node ¤ÈƱ°ì¥Õ¥©¡¼¥Þ¥Ã¥È</li>
    
<li>bos: ·ÁÂÖÁDzòÀϤηë²Ì¤ËÀè¤À¤Ã¤Æ½ÐÎÏ (header
ŪÌò³ä), ¥Ç¥Õ¥©¥ë¥È¤Ï¶õʸ»ú</li>

<li>eos: ·ÁÂÖÁDzòÀϤηë²Ì¤Î¸å¤Ë½ÐÎÏ (footer ŪÌò³ä),
¥Ç¥Õ¥©¥ë¥È¤Ï "EOS\n"</li>
</ul>

<p>ÌÀ¼¨Åª¤Ë»ØÄꤵ¤ì¤Ê¤¤¾ì¹ç,
¤½¤ì¤¾¤ì¤Î¥Ç¥Õ¥©¥ë¥Èʸ»úÎ󤬻ÈÍѤµ¤ì¤Þ¤¹.</p>

<p>¤³¤ì¤é¤Ï, °Ê²¼¤Î 2¤Ä¤ÎÊýË¡¤Ç»ØÄꤷ¤Þ¤¹.</p>

<ul>
<li>¥³¥Þ¥ó¥É¥é¥¤¥ó¤«¤é 

<pre>
% mecab --node-format=STR --bos-format=STR --eos-format=STR --unk-format=STR
</pre>
</li>

<li>mecabrc ¤Ëµ­½Ò¤¹¤ë¾ì¹ç 

<p>Ǥ°Õ¤Îʸ»úÎó KEY ¤ò»È¤¤, mecabrc
¤Ë°Ê²¼¤Î¤è¤¦¤ËÄêµÁ.</p>

<pre>
node-format-KEY = STR
unk-format-KEY = STR
eos-format-KEY = STR
bos-format-KEY = STR
</pre>

<p>¤³¤Î KEY ¤ò¥³¥Þ¥ó¥É¥é¥¤¥ó¤«¤é¸Æ¤Ó½Ð¤¹.</p>

<pre>
% mecab -Okey 
</pre>
</li>
</ul>

<h2>½ÐÎÏ¥Õ¥©¡¼¥Þ¥Ã¥È</h2>

<table>
<tr class="odd">
<td>%s</td>
<td>·ÁÂÖÁǼïÎà (0: Ä̾ï, 1: ̤Ãθì, 2:ʸƬ, 3:ʸËö)
</td>
</tr>

<tr class="even">
<td>%S</td>
<td>ÆþÎÏʸ</td>
</tr>

<tr class="odd">
<td>%L</td>
<td>ÆþÎÏʸ¤ÎŤµ</td>
</tr>

<tr class="even">
<td>%m</td>
<td>·ÁÂÖÁǤÎɽÁØʸ»úÎó</td>
</tr>

<tr class="odd">
<td>%M</td>
<td>·ÁÂÖÁǤÎɽÁØʸ»úÎó, ¤¿¤À¤·¶õÇòʸ»ú¤â´Þ¤á¤Æ½ÐÎÏ (%pS ¤ò»²¾È¤Î¤³¤È)</td>
</tr>

<tr class="even">
<td>%h</td>
<td>ÁÇÀ­¤ÎÆâÉô ID</td>
</tr>

<tr class="odd">
<td>%%</td>
<td>% ¤½¤Î¤â¤Î</td>
</tr>

<tr class="even">
<td>%c</td>
<td>ñ¸ìÀ¸µ¯¥³¥¹¥È</td>
</tr>

<tr class="odd">
<td>%H</td>
<td>ÁÇÀ­ (ÉÊ»ì, ³èÍÑ, Æɤß) Åù¤ò CSV
¤Çɽ¸½¤·¤¿¤â¤Î</td>
</tr>

<tr class="even">
<td>%t</td>
<td>ʸ»ú¼ï id </td>
</tr>

<tr class="odd">
<td>%P</td>
<td>¼þÊÕ³ÎΨ (-l2 ¥ª¥×¥·¥ç¥ó¤ò»ØÄꤷ¤¿¤È¤­¤Î¤ßÍ­¸ú)</td>
</tr>

<tr class="even">
<td>%pi</td>
<td>·ÁÂÖÁǤËÉÕÍ¿¤µ¤ì¤ë¥æ¥Ë¡¼¥¯¤ÊID</td>
</tr>

<tr class="odd">
<td>%pS</td>
<td>¤â¤··ÁÂÖÁǤ¬¶õÇòʸ»úÎó¤Ç»Ï¤Þ¤ë¾ì¹ç¤Ï, ¤½¤Î¶õÇòʸ»úÎó¤òɽ¼¨ %pS%m ¤È %M ¤ÏƱ°ì</td>
</tr>

<tr class="even">
<td>%ps</td>
<td>³«»Ï°ÌÃÖ</td>
</tr>

<tr class="odd">
<td>%pe</td>
<td>½ªÎ»°ÌÃÖ</td>
</tr>

<tr class="even">
<td>%pC</td>
<td>1¤ÄÁ°¤Î·ÁÂÖÁǤȤÎÏ¢ÀÜ¥³¥¹¥È</td>
</tr>

<tr class="odd">
<td>%pw</td>
<td>%c ¤ÈƱ¤¸</td>
</tr>

<tr class="even">
<td>%pc</td>
<td>Ï¢ÀÜ¥³¥¹¥È + ñ¸ìÀ¸µ¯¥³¥¹¥È (ʸƬ¤«¤éÎßÀÑ)</td>
</tr>

<tr class="odd">
<td>%pn</td>
<td>Ï¢ÀÜ¥³¥¹¥È + ñ¸ìÀ¸µ¯¥³¥¹¥È (¤½¤Î·ÁÂÖÁÇñÆÈ, %pw + %pC)</td>
</tr>

<tr class="even">
<td>%pb</td>
<td>ºÇŬ¥Ñ¥¹¤Î¾ì¹ç *, ¤½¤ì°Ê³°¤Ï ' '</td>
</tr>

<tr class="odd">
<td>%pP</td>
<td>¼þÊÕ³ÎΨ (-l2 ¥ª¥×¥·¥ç¥ó¤ò»ØÄꤷ¤¿¤È¤­¤Î¤ßÍ­¸ú)</td>
</tr>

<tr class="even">
<td>%pA</td>
<td>blpha, forward log ³ÎΨ (-l2 ¥ª¥×¥·¥ç¥ó¤ò»ØÄꤷ¤¿¤È¤­¤Î¤ßÍ­¸ú)</td>
</tr>

<tr class="odd">
<td>%pB</td>
<td>beta, backward log ³ÎΨ (-l2 ¥ª¥×¥·¥ç¥ó¤ò»ØÄꤷ¤¿¤È¤­¤Î¤ßÍ­¸ú)</td>
</tr>

<tr class="even">
<td>%pl</td>
<td>·ÁÂÖÁǤÎɽÁØʸ»úÎó¤È¤·¤Æ¤ÎŤµ, strlen (%m) ¤ÈƱ°ì</td>
</tr>

<tr class="odd">
<td>%pL</td>
<td>·ÁÂÖÁǤÎɽÁØʸ»úÎó¤È¤·¤Æ¤ÎŤµ, ¤¿¤À¤·¶õÇòʸ»úÎó¤â´Þ¤à, strlen(%M) ¤ÈƱ°ì</td>
</tr>

<tr class="even">
<td>%phl</td>
<td>º¸Ê¸Ì® id</td>
</tr>

<tr class="odd">
<td>%phr</td>
<td>±¦Ê¸Ì® id</td>
</tr>

<tr class="even">
<td>%f[N]</td>
<td>csv ¤Çɽµ­¤µ¤ì¤¿ÁÇÀ­¤Î NÈÖÌܤÎÍ×ÁÇ</td>
</tr>

<tr class="odd">
<td>%f[N1,N2,N3...]</td>
<td>N1,N2,N3ÈÖÌܤÎÁÇÀ­¤ò, "," ¤ò
¥Ç¥ê¥ß¥¿¤È¤·¤Æɽ¼¨</td>
</tr>

<tr class="even">
<td>%FC[N1,N2,N3...]</td>
<td>N1,N2,N3ÈÖÌܤÎÁÇÀ­¤ò, C ¤ò
¥Ç¥ê¥ß¥¿¤È¤·¤Æɽ¼¨.<br>
¤¿¤À¤·, Í×ÁǤ¬ ¶õ¤Î¾ì¹ç¤Ï°Ê¹ßɽ¼¨¤¬¾Êά¤µ¤ì¤ë.
(Îã)F-[0,1,2]</td>
</tr>

<tr class="odd">
<td>\0 \a \b \t \n \v \f \r \\</td>
<td>Ä̾ï¤Î ¥¨¥¹¥±¡¼¥×ʸ»úÎó</td>
</tr>

<tr class="even">
<td>\s</td>
<td>' ' (Ⱦ³Ñ¥¹¥Ú¡¼¥¹)<br>
 ÀßÄê¥Õ¥¡¥¤¥ë¤Ëµ­½Ò¤¹¤ë¤È¤­¤Ë»ÈÍÑ</td>
</tr>
</table>

<h2>Îã</h2>
<p>
dicrc ¤è¤êÈ´¿è¤·¤¿Îã 
</p>
<pre>
; yomi
node-format-yomi = %pS%f[7]
unk-format-yomi = %M
eos-format-yomi  = \n

; simple
node-format-simple = %m\t%F-[0,1,2,3]\n
eos-format-simple  = EOS\n

; csv
node-format-csv = %m,%f[7],%f[8],%f[6],%F-[0,1,2,3],%f[4],%f[5]\n
unk-format-csv  = %m,%m,%m,%f[6],%F-[0,1,2,3],,\n
eos-format-csv  = EOS,,,,,,\n

; ChaSen
node-format-chasen = %m\t%f[7]\t%f[6]\t%F-[0,1,2,3]\t%f[4]\t%f[5]\n
unk-format-chasen  = %m\t%m\t%m\t%F-[0,1,2,3]\t\t\n
eos-format-chasen  = EOS\n
</pre>

<h2>Ãí°Õ»ö¹à</h2>

<p>¤ï¤«¤Á½ñ¤­½ÐÎÏ (-Owakati), 
¥Ç¥Õ¥©¥ë¥È¤Î½ÐÎÏ, ½ÐÎÏ¥À¥ó¥× (-Odump) ¤Ï
¹â®À­¤òµ¾À·¤Ë¤·¤¿¤¯ ¤Ê¤¤¤¿¤á¤Ë, ¥Ï¡¼¥É¥³¡¼¥Ç¥£¥ó¥°¤µ¤ì¤Æ¤¤¤Þ¤¹.</p>

<hr>
<p>$Id: format.html 65 2007-01-30 00:52:53Z taku-ku $;</p>
</body>
</html>