JESCThis page has moved to https://nlp.stanford.edu/projects/jesc/
Tanaka Corpus - EDRDG Wiki
Introduction This page provides some brief documentation for the Tanaka Corpus of parallel Japanese-English sentences, and in particular the modification and editing that has been carried out to enable use of the corpus as a source of examples in the WWWJDIC dictionary server and other systems. The corpus was compiled by Professor Yasuhito Tanaka at Hyogo University and his students, as described
Reordering with Source Language Collocations
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pages 1036–1044, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Reordering with Source Language Collocations Zhanyi Liu1,2 , Haifeng Wang2 , Hua Wu2 , Ting Liu1 , Sheng Li1 1 Harbin Institute of Technology, Harbin, China 2 Baidu Inc., Beijing, China {liuzhanyi, wanghaifeng
A Joint Sequence Translation Model with Integrated Reordering
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pages 1045–1054, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics A Joint Sequence Translation Model with Integrated Reordering Nadir Durrani Helmut Schmid Alexander Fraser Institute for Natural Language Processing University of Stuttgart {durrani,schmid,fraser}@ims.uni-stut
統計的機械翻訳ã®ãƒ„ールGIZA++を使ã£ã¦ã¿ãŸ - nokunoã®æ—¥è¨˜
GIZA++を使ã£ã¦Wikipedia対訳コーパスをアライメントã™ã‚‹ã¾ã§ã‚„ã£ã¦ã¿ã¾ã—ãŸã€‚Wikipedia日英京都関連文書対訳コーパスWikipedia日英京都関連文書対訳コーパスGIZA++ giza-pp - Project Hosting on Google CodeãªãŠã€ç’°å¢ƒã¯Macbook Airã§ã‚‚å‹•ã„ãŸã®ã§ã™ãŒã€é‡ã‹ã£ãŸã®ã§ã‚µãƒ¼ãƒãƒ¼ã®CentOSã§å‹•ã‹ã—ã¾ã—ãŸã€‚# 対訳コーパスをダウンãƒãƒ¼ãƒ‰ã—ã¦æ•´å½¢$ wget http://alaginrc.nict.go.jp/WikiCorpus/cgi-bin/dl1.cgi$ tar xfz wiki_corpus_2.0.tar.gz$ cd wiki_corpus_2.0$ mkdir parallel$ cat */*.xml | egrep '^' | sed -e "s///g" | sed -e "s///g" > pa
Book: Statistical Machine Translation
Philipp Koehn Hardcover, 488 pages Publisher: Cambridge University Press ISBN-10: 0521874157 ISBN-13: 978-0521874151 Content (more slides will be added over the next weeks) Chapter 1: Introduction Chapter 2: Words, Sentences, Corpora Chapter 3: Probability Theory Chapter 4: Word-Based Models slides Chapter 5: Phrase-Based Models slides Chapter 6: Decoding slides Chapter 7: Language Models slides C
IBM Model-1 ã®å¼ã®èª¬æ˜Ž
8. IBM Model-1 ã®å¼ã®èª¬æ˜Ž 内山将夫@NICT mutiyama@nict.go.jp 1 IBM-Mode1ã®å¼ã®èª¬æ˜Žã®ã¾ãˆã« Q: 何ã®ãŸã‚ã«ç¢ºçŽ‡ãƒ¢ãƒ‡ãƒ«ã‚’利用ã™ã‚‹ã‹ A: • å˜èªžå¯¾å¿œã®ç¢ºçŽ‡ã‚„ • å˜èªžå¯¾å¿œè‡ªä½“を求ã‚ã‚‹ãŸã‚ å˜èªžå¯¾å¿œã®ç¢ºçŽ‡ï¼š 「ãŠé‡‘ã€ã¯ã€Œcashã€ã¨ã€Œmoneyã€ã®ã©ã¡ã‚‰ã«è¨³ã•ã‚Œã‚‹ã“ ã¨ãŒå¤šã„ã‹ï¼Ÿ å˜èªžå¯¾å¿œè‡ªä½“を求ã‚ã‚‹ãŸã‚： 「今日ã€ã€Œã¯ã€ã€Œè‰¯ã„ã€ã€Œå¤©æ°—ã€ã€Œã ã€ã¨ã€ŒItã€ã€Œisã€ã€Œï¬ne〠「todayã€ã§ã¯ï¼Œã€Œä»Šæ—¥ã€ã¯ã©ã®å˜èªžã«å¯¾å¿œã™ã‚‹ã‹ï¼Ÿ 2 å˜èªžå¯¾å¿œè‡ªä½“を求ã‚ã‚‹ã«ã¯ã©ã†ã™ã‚‹ã‹ æ¡ä»¶ï¼š 英文eã¨ä»æ–‡f ãŒä¸Žãˆã‚‰ã‚Œã¦ã„ã¦ï¼Œå˜èªžå¯¾å¿œaã«ã¤ã„ã¦ï¼Œ P(f, a|e)ãŒè¨ˆç®—ã§ãã‚‹ã¨ã™ã‚‹ 求ã‚るも㮠ˆa : ˆa = arg maxa P(f, a|e) ˆaã¯ï¼ŒP(f, a|e)を最大化ã™ã‚‹ã‚¢ãƒ©ã‚¤ãƒ³ãƒ¡ãƒ³ãƒˆã§ã‚る．㓠れã¯æœ€ã‚‚確率ãŒé«˜ã„アラインメントã§ã‚る．
シックス・アパート関æ°ãŒèªžã£ãŸæ–°ãƒ–ãƒã‚°ã‚µãƒ¼ãƒ“ス「Voxã€ã®ã™ã¹ã¦ - CNET Japan
シックス・アパートã¯ã€å€‹äººå‘ã‘ã®æ–°ãƒ–ãƒã‚°ã‚µãƒ¼ãƒ“ス「Voxã€ã‚’10月28æ—¥ã«é–‹å§‹ã—ãŸã€‚ç„¡æ–™ã§åˆ©ç”¨ã§ãã‚‹ã»ã‹ã€åˆå¿ƒè€…ã§ã‚‚ç°¡å˜ã«ãƒ–ãƒã‚°ã‚’続ã‘ã¦ã„ããŸã‚ã®ã•ã¾ã–ã¾ãªä»•çµ„ã¿ãŒç››ã‚Šè¾¼ã¾ã‚Œã¦ã„る。ã¾ãŸã€ãƒ–ãƒã‚°ã®å†…容をã€è¨˜äº‹ã‚„写真å˜ä½ã§å…¬é–‹ç¯„囲ã®åˆ¶é™ã‚’付ã‘ã‚‹ã“ã¨ã§å®‰å…¨æ€§ã‚’高ã‚ã¦ã„る。 ブãƒã‚°ã‚½ãƒ•ãƒˆã®Movable Typeやブãƒã‚°ã‚µãƒ¼ãƒ“スã®TypePadã‚’æä¾›ã—ã¦ããŸã‚·ãƒƒã‚¯ã‚¹ãƒ»ã‚¢ãƒ‘ートãŒé³´ã‚Šç‰©å…¥ã‚Šã§é–‹å§‹ã—ãŸæ–°ã‚µãƒ¼ãƒ“スをåŒç¤¾ã¯ã©ã®ã‚ˆã†ã«å±•é–‹ã—ã¦ã„ã戦略ãªã®ã‹ã€‚代表å–ç· å½¹ã§ã‚る関信浩æ°ã«èžã„ãŸã€‚ --シックス・アパートã§ã¯Movable Typeã‚„TypePadã‚’æä¾›ã—ã¦ãã¾ã—ãŸã€‚Voxã¯ä»Šã¾ã§ã®è£½å“ã¨ä½•ãŒé•ã„ã¾ã™ã‹ã€‚ ブãƒã‚°ã¨ã„ã†ã®ã¯ã‚‚ã¨ã‚‚ã¨ã‚¤ãƒ³ã‚¿ãƒ¼ãƒãƒƒãƒˆä¸Šã§æƒ…å ±ã‚’ç™ºä¿¡ã™ã‚‹ãƒ„ールã ã£ãŸã¨æ€ã„ã¾ã™ã€‚今回ã®æ£å¼ã‚µãƒ¼ãƒ“スã¯ã€æ—¥æœ¬ã®ã»ã‹ã«ã‚‚米国ã€ãƒ•ãƒ©ãƒ³ã‚¹ã§åŒæ™‚ã«é–‹å§‹ã—ã¦ã„ã¾ã™ãŒã€æµ·å¤–ã§ãƒ–ãƒã‚°ã¨ã„ã†ã¨ãƒ‹ãƒ¥ãƒ¼ã‚¹ãƒ¡ãƒ‡ã‚£ã‚¢
My RSS 管ç†äºº ブãƒã‚°ï¼ˆå·¥äº‹äºˆå®šï¼‰: ブãƒã‚°è¨˜äº‹æŠ•ç¨¿ãŒæ¿€ã—ã楽ã«ãªã‚‹ Windows Live Writer
ã“ã‚Œã¾ã§å†™çœŸã¤ãã®ãƒ–ãƒã‚°è¨˜äº‹ã‚’投稿ã™ã‚‹ã®ãŒã¨ã¦ã‚‚é¢å€’ã ã£ãŸã®ã§ã™ãŒã€ã“ã® Windows Live Writer ãŒè§£æ±ºã—ã¦ãã‚Œãã†ã§ã™ã€‚ ・・・ã¨ã„ã†ã‹ã€ã“ã‚Œã¯ã‚‚ã†æ‰‹æ”¾ã›ãªããªã‚‹äºˆæ„Ÿã€‚ã“ã®è¨˜äº‹ã‚‚ Windows Live Writer ã§æ›¸ã„ã¦ã„ã¾ã™ã€‚ Windows Live Writer 㯠WYSIWYG (ブãƒã‚°ã«è¡¨ç¤ºã•ã‚Œã‚‹çŠ¶æ…‹ã§è¨˜äº‹ã®ç·¨é›†ãŒã§ãã‚‹) ã®ã‚¨ãƒ‡ã‚£ã‚¿ã§ã™ã€‚ ãªã‚“ã¨è‡ªå‹•çš„ã«ãƒ–ãƒã‚°ã®ã‚¹ã‚¿ã‚¤ãƒ«ã‚·ãƒ¼ãƒˆã‚’å–å¾—ã—ã¦ãれるã®ã§ã€æœ¬å½“ã«è‡ªåˆ†ã®ãƒ–ãƒã‚°ã‚’直接編集ã—ã¦ã„ã‚‹ã‹ã®ã‚ˆã†ã«è¨˜äº‹ã‚’書ãã“ã¨ãŒã§ãã¾ã™ã€‚ ↓ã“ã‚“ãªæ„Ÿã˜ã€‚MyRSS 管ç†äººãƒ–ãƒã‚°ã®ã‚¹ã‚¿ã‚¤ãƒ«ã‚’ãã®ã¾ã¾ä½¿ã£ã¦ç·¨é›†ã§ãã¾ã™ã€‚ ã•ã‚‰ã«ç”»åƒã®è¿½åŠ ãŒã¨ã¦ã‚‚ç°¡å˜ã§ã™ã€‚ ç”»åƒãƒ•ã‚¡ã‚¤ãƒ«ã‚’指定ã™ã‚‹ã ã‘ã§è¨˜äº‹ä¸ã«ç°¡å˜ã«æŒ¿å…¥ã§ãã‚‹ã®ã¯ã‚‚ã¡ã‚ã‚“ã€ç”»é¢ã‚·ãƒ§ãƒƒãƒˆã‚„ファイルをコピーペーストã™ã‚‹ã ã‘ã§ã‚‚è¿½åŠ ã§ãã¾ã™ã€‚ã—ã‹ã‚‚ç”»åƒã‚µã‚¤ã‚ºã‚‚ä»»æ„ã«å¤‰æ›´ã§ãã¾ã™ã€‚
1
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
https://www.logos.t.u-tokyo.ac.jp/~eriguchi/demo/tree2seq/index.php
[スタパ齋藤ã®ã€Œã‚¹ã‚¿ãƒ‘ブãƒã‚°ã€] ã†ã£ã€ã¨æ€ã£ã¦ãƒžã‚¹ã‚ングテープè¡å‹•è²·ã„![[スタパ齋藤ã®ã€Œã‚¹ã‚¿ãƒ‘ブãƒã‚°ã€] ã†ã£ã€ã¨æ€ã£ã¦ãƒžã‚¹ã‚ングテープè¡å‹•è²·ã„](https://cdn-ak-scissors.b.st-hatena.com/image/square/a7f2e98cdff0f56d9e1c60ddb55346bb08e0514f/height=288;version=1;width=512/http%3A%2F%2Fk-tai.watch.impress.co.jp%2Fimg%2Fktw%2Flist%2F670%2F729%2Fimportant_image.jpg)
NaistMT's Wiki - Tutorials for Beginners
Joint Parsing and Alignment with Weakly Synchronized Grammars David Burkett, John Blitzer, and Dan Klein {dburkett,blitzer,klein}@cs.berkeley.edu Statistical Machine Translation Rules Xinhua News Agency æ–°åŽç¤¾ ( End ) （ 完 ） Beijing , February 13
ACL Anthology
CiNii 論文 - 機械翻訳最新事情 : (上)統計的機械翻訳入門
http://moblog.pakuto.com/archives/travel/
{{#tags}}- {{label}}
{{/tags}}