Code Archive Skip to content Google About Google Privacy Terms
FrontPage / è¨èªå¦ç100æ¬ãã㯠3 ç§å¾ã« NLP 100 Drill Exercises ã«ç§»åãã¾ãã (移åããªãå ´åã¯ãä¸ã®ãªã³ã¯ãã¯ãªãã¯ãã¦ãã ããã) © Inui Laboratory 2010-2018 All rights reserved. ç 究室紹ä»/About Us éå»ã«å¨ç±ããã¡ã³ãã¼ Members ç 究室ç°å¢ Lab Facilities âç 究ä¼/Research Meetings æ¦è¦ Overview ç·åç ç©¶ä¼ Research Seminar æå³ç ç©¶ä¼ SIG Semantics è«è©±ç ç©¶ä¼ SIG Discourse ç¥èç²å¾ç ç©¶ä¼ SIG Knowledge Acquisition Embeddingç ç©¶ä¼ SIG Embedding KIAI Knowledge-Intensive Artificial Intellige
æ¦è¦ Javaã®æ¯è¼çæ°ããå½¢æ ç´ è§£æå¨ãKuromojiã lucene-gosenãGomokuã®ããã«è¾æ¸å å ã§ãjarãè½ã¨ãã°ãã®å ´ã§å©ç¨ã§ããUnidicã«å¯¾å¿ãã¦ãã¦ãã½ã¼ã¹ãLuceneã®trunkã«ã³ãããããã¦ããã¨ãããä½ãã¨æ°ã«ãªãç¹å¾´ã®æã¡ä¸»ã è¤æ°ã®ã¢ã¼ããæã£ã¦ããããã§ãSearchã¢ã¼ãã使ãã¨ãæ¥æ¬çµæ¸æ°èãããæ¥æ¬ | çµæ¸ | æ°èãã®ããã«æ¤ç´¢ã§å©ç¨ããããå½¢ã«ã°ããã¦è§£æãã¦ãããããExtendedã¢ã¼ãã使ãã¨æªç¥èªãuni-gramã«ãã¦ããããããããããã ä»æ¥ã¯ãããªKuromojiããã®å°å ¥ããç°¡æãªä½¿ãæ¹ã¾ã§ãããã£ã¨è¿½ãããã¦ã¿ãã å°å ¥ ã¾ãã¯ä¸è¨ãã¼ã¸ãããã¦ã³ãã¼ããä»åã¯kuromoji-0.7.5.tar.gzãå©ç¨ã Downloads - atilika/kuromoji https://github.com/at
ãããã話ããè¨èªå¦ãã«åé¡ããã®ã¯ã¨ã£ã¦ãã¨ã£ã¦ãå¾®å¦ãªæ°ããã¾ãããIPAè¾æ¸ã«ãããä»®å®ç¸®ç´ã¨ChaSenã¨MeCabã«ããããã®æ±ãã®ç¸éã«ã¤ãã¦ã¾ã¨ãã¦ããããã¨æãã¾ããã¨ãããååã®ãã¨ã£ã¦ãä¸éå端ã ã£ããééã£ã¦ãããããã®ã§åçãã¦ã¡ããã¨æ¸ãããã¨æãã¾ãã ã¾ãããIPAè¾æ¸ï¼åè©åé¡ãåè©-代åè©-縮ç´ãã«ã¤ãã¦ãã§è§¦ããããã«ãIPAè¾æ¸ã«ããããåè©-代åè©-縮ç´ãã¨ã¯æ¬¡ã®ããã«å®ç¾©ããã¦ãã¾ãã 5.1.10 åè©-代åè©-ç¸®ç´ ï¼ ä»£åè©ã¨ä¿å©è©ãã¯ãã®çµã¿åããã§ï¼ç縮ããå½¢ï¼å£èªï¼ï¼ ä¾ï¼ ããããããããããããããããããããããããããã ã¤ã¾ãããããããï¼ããããï¼ãã¯ãã®ããã«è¦åããã®ã縮ç´ã§ããIPAè¾æ¸ã®ä½ç³»å ã§ã¯ãããããã¯åè©åé¡ãåè©-代åè©-縮ç´ãã«ã«ãã´ãªããã¦ãã¾ããã¾ãåå触ããããã«ããããããªã©ä¾ã«æãããããã®ãå ¨
çªç¶ã§ããï¼mecabã®è¾æ¸ (mecab-ipadic) ãããã©ã«ãã®ã¾ã¾ä½¿ã£ã¦ï¼mecabæå¤ã¨ä½¿ãããã¨ãæå¥è¨ã£ã¦ãæªãåã¯ãããããï¼ mecab-ipadic ã¯æ¯è¼çãè¡åã®ããæ¥æ¬èªããã¼ã¹ã«ä½ããã¦ããã®ã§ï¼ãã®ã¾ã¾ã§ã¯ webä¸ã®å£èªæä½ã®ããã¹ãã¯ãã¾ãæ±ããªããã¨ãããã¾ããæ¬æ¥ã¯æ師ãã¼ã¿ãç¨æãï¼å¦ç¿ãããã¨ãã£ãææ³ã使ãã®ãæ£æ»æ³ã ã¨æãã¾ããï¼ã¨ããããåè©ãå å®ãããã ãã§ãå®ç¨åº¦ã¯ã ãã¶ä¸ããã§ãããã 人éã®è©±ãè¨èªã«ã¯ï¼åè©ã®èªå¹¹ãåè©ã«ã¯æ¥ã æ°ããèªå½ãå¢ãããã©ï¼å©è©ãæ´»ç¨ã®ã«ã¼ã«ã¯ç°¡åã«ã¯å¤åããªãï¼ã¨ããç¹æ§ãããã¾ããç¹ã«ããã¾æãã¤ã¶ãããã¦ããåèªã©ã³ãã³ã°ãã¨ãã£ãéè¨ããããããªå ´åã¯ï¼åè©ã®ç¯å²ã®åãåºãããééããªããã°ãããªãã®çµæãåºãããã¨ãå¤ãã®ã§ãã ãã ï¼è¾æ¸ã¸ã®åèªè¿½å ã¯ããã«ããéãç°¡åã«ã§ããã®ã§ããï¼åèª
2. â¾èªâ¼°å·±ç´¹ä» lï¬â¯ æµ·éâãè£ä¹  (@unnonouno) lï¬â¯ unno/no/uno lï¬â¯ ç 究éçºé¨â¾¨éâããªãµã¼ãã£ã¼ lï¬â¯ å°â¾¨é lï¬â¯ â¾èªç¶â¾è¨èªå¦ç理 lï¬â¯ ããã¹ããã¤ãã³ã° lï¬â¯ è·æ´ lï¬â¯ 2008/4~2011/3 â½æ¥æ¬ã¢ã¤ã»ãã¼ã»ã¨ã ï¼æ ªï¼æ±äº¬ åºç¤ç 究æ lï¬â¯ 2011/4~ ç¾è· 2 3. ä»â½æ¥ã®çºè¡¨ã®â½¬ç®ç lï¬â¯ å½¢æ ç´ è§£æå¨ã®ä¸ã§ä½ãâ¾è¡ï¨ããã¦ããã lï¬â¯ ã³ã¹ãæ⼩å°å, HMM, MEMM, CRF etc. , lï¬â¯ JUMAN, Chasen, MeCab, etc. lï¬â¯ ã»ã»ã»ã ãã ã¨ããããã®ã§ãææ°ã®â¼¿ææ³ã¨é å»ã®â¼¿ææ³ãã¾ã¨ãã lï¬â¯ ç¾å¨ã®åé¡ç¹ã«é¢ãã¦ãã¾ã¨ãã 3
èªç¶è¨èªå¦çãæ´»ç¨ããwebãµã¼ãã¹éçºã«é¢ãã£ã¦5年以ä¸çµã£ããããæ©ä¼ãªã®ã§ããã¾ã§ãæ¯ãè¿ã£ã¦å½¹ã«ç«ã£ãã¨æã5åãã¡ã¢ãã¦ããã 1.ç çã®ããã°ã©ãã³ã°âæ¬è³ªãè¦æããã¢ã«ã´ãªãºã ã¨ãã¼ã¿æ§é ã¾ãã¯ãããæåãªæ¬ãªã®ã§ç¥ã£ã¦ãã人ãå¤ãã¨æããç°¡åã«èª¬æããã¨ã¡ãã£ã¨åã«ããã§ã«ãæ¨å®ãã¨ããååã§æµè¡ã£ããããªããã¼ã¿ããå¿ è¦ãªæ°å¤ãæ¦ç®ããæ¹æ³ããåé¡ãèµ·ããã¨ãã«åé¡ç¹ãã©ãã«ããã®ãï¼æå°ã®å´åã§è§£æ±ºããã«ã¯ã©ãããããã°ããã®ãï¼ãªã©ãæ¸ãã¦ããããwebãµã¼ãã¹ã§èªç¶è¨èªå¦çã ï¼ãã¨ããã¨ç¡éã«å¤¢ãåºãããã¡ãªã®ã§ãã©ããããã¼ã¿ã使ããã®ãããããã©ãããå½¢ã«ãã£ã¦ããã°ã¤ã±ã¦ããµã¼ãã¹ã«ãªãã®ããããã¯ã©ã®ãããã®æéã§å®ç¾ã§ããããã¨ãããã¨ãèããå¿ è¦ããããããããããã§æ¬æ¸ã¯çã£å ã«èªãã¹ãä¸åãªã®ã§ã¯(ä½è«ã ããã©ã以åM << Nãªãã¼ã¿ã«å¯¾ãã¦O(
ã¯ããã« ãã®ææ¸ã¯ã Steven Bird, Ewan Klein, Edward Loper è è©å æ£äººãä¸å±± æ¬åºãæ°´é è²´æã訳 ãå ¥é èªç¶è¨èªå¦çã O'Reilly Japan, 2010. ã®ç¬¬12ç« ãPython ã«ããæ¥æ¬èªèªç¶è¨èªå¦çãããåæ¸ Natural Language Processing with Python ã¨åã Creative Commons Attribution Noncommercial No Derivative Works 3.0 US License ã®ä¸ã§å ¬éãããã®ã§ãã åæ¸ã§ã¯ä¸»ã«è±èªã対象ã¨ããèªç¶è¨èªå¦çãåãæ±ã£ã¦ãã¾ããå 容ãèãæ¹ã®å¤ãã¯è¨èªã«ä¾åããªããã®ã§ã¯ããã¾ãããåèªã®åãã¡æ¸ããããªãç¹ãçµ±èªæ§é çã®éããããæ¥æ¬èªã対象ã¨ããå ´åãããã¤ãæ°ãã¤ããªããã°ãããªãç¹ãããã¾ããæ¥æ¬èªãæ±ãå ´åã«ã
2. ç§ï¼ä½è¤æç´ï¼ã®èªå·±ç´¹ä»ååï¼ä½è¤æç´ï¼ãã¨ãã¨ãã®ãï¼ID : overlastï¼Twitter : @overlastï¼key : èªç¶è¨èªå¦ç/æ©æ¢°å¦ç¿/æ¤ç´¢/å§ç¸®/é åºå¦ç¿blog : Overlasting::Life(http://diary.overlasting.net/) ç¥æ´2005å¹´4æã2008å¹´3æï¼æ±å·¥å¤§ã®å¥¥æç 究室èªç¶è¨èªå¦çï¼æ¯è¼é¢ä¿æ½åºï¼ã®ç 究2008å¹´5æã:æ大æãã¼ã¿ã«ãµã¤ãèªç¶è¨èªå¦çã»æ©æ¢°å¦ç¿æè¡ãWebææ¸ã«å¿ç¨é¡ä¼¼æååæ¤ç´¢ã©ã¤ãã©ãªã®ç 究ã»éçºã¹ãã«è¨æ£ã·ã¹ãã ã®ç 究ã»éçº2
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
å¦çãå®è¡ä¸ã§ã
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}