My NAACL 2013 list...
my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) I feel a bit odd doing my "what I liked at NAACL 2013" as one of the program chairs, but not odd enough to skip what seems to be the most popular type of post :). First, though, since Katrin Kirchhoff (my co-chair) and I never got a chance
ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—ã®çµ‚了日を2020å¹´1月31æ—¥(金)ã«æ±ºå®šã—ã¾ã—㟠- ã¯ã¦ãªã®å‘ŠçŸ¥
ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—ã®çµ‚了日を2020å¹´1月31æ—¥(金)ã«æ±ºå®šã—ã¾ã—㟠以下ã®ã‚¨ãƒ³ãƒˆãƒªã®é€šã‚Šã€ä»Šå¹´æœ«ã‚’目処ã«ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—を終了予定ã§ã‚る旨をãŠçŸ¥ã‚‰ã›ã—ã¦ãŠã‚Šã¾ã—ãŸã€‚ 2019年末を目処ã«ã€ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—ã®æ供を終了ã™ã‚‹äºˆå®šã§ã™ - ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—日記 ã“ã®ãŸã³ã€æ£å¼ã«çµ‚了日を決定ã„ãŸã—ã¾ã—ãŸã®ã§ã€ä»¥ä¸‹ã®é€šã‚Šã”確èªãã ã•ã„。 終了日: 2020å¹´1月31æ—¥(金) エクスãƒãƒ¼ãƒˆå¸Œæœ›ç”³è«‹æœŸé™:2020å¹´1月31æ—¥(金) 終了日以é™ã¯ã€ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—ã®é–²è¦§ãŠã‚ˆã³æŠ•ç¨¿ã¯è¡Œãˆã¾ã›ã‚“。日記ã®ã‚¨ã‚¯ã‚¹ãƒãƒ¼ãƒˆãŒå¿…è¦ãªæ–¹ã¯ä»¥ä¸‹ã®è¨˜äº‹ã«ã—ãŸãŒã£ã¦æ‰‹ç¶šãã‚’ã—ã¦ãã ã•ã„。 ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—ã«æŠ•ç¨¿ã•ã‚ŒãŸæ—¥è¨˜ãƒ‡ãƒ¼ã‚¿ã®ã‚¨ã‚¯ã‚¹ãƒãƒ¼ãƒˆã«ã¤ã„㦠- ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—日記 ã”利用ã®ã¿ãªã•ã¾ã«ã¯ã”迷惑をãŠã‹ã‘ã„ãŸã—ã¾ã™ãŒã€ã©ã†ãžã‚ˆã‚ã—ããŠé¡˜ã„ã„ãŸã—ã¾ã™ã€‚ 2020-06-25 追記 ã¯ã¦ãªã‚°ãƒ«ãƒ¼ãƒ—日記ã®ã‚¨ã‚¯ã‚¹ãƒãƒ¼ãƒˆãƒ‡ãƒ¼ã‚¿ã¯2020å¹´2月28
機械å¦ç¿’ × MapReduce - ny23ã®æ—¥è¨˜
個人的ãªèˆˆå‘³ã¨ã„ã†ã‚ˆã‚Šï¼Œé›‘用絡ã¿ã§çœºã‚ãŸè«–æ–‡ã®ç´¹ä»‹ï¼Žæ©Ÿæ¢°å¦ç¿’アルゴリズムを並列分散化ã™ã‚‹ã¨ã„ã†è©±ãŒæœ€è¿‘æµè¡Œã£ã¦ã„るよã†ã ．全然網羅的ã§ã¯ãªã„ã‘ã©ï¼Œèª°ã‹ã®å½¹ã«ç«‹ã¤ã‹ã‚‚知れãªã„ã®ã§ï¼Œå¹¾ã¤ã‹ãƒ¡ãƒ¢ã—ã¦ãŠã．ã¾ãšå¤å…¸çš„ã«ã¯ã“れ， Map-reduce for machine learning on multicore (NIPS 2006) å¤å…¸çš„ãªæ©Ÿæ¢°å¦ç¿’アルゴリズム（ãƒãƒƒãƒå¦ç¿’）ã®å¤šãã¯ï¼ŒStatistical Query Model ã§è¨˜è¿°ã§ãã¦ï¼Œãれら㯠summation form ã§è¨˜è¿°ã§ãã‚‹ (ã‹ã‚‰ï¼ŒMapReduce ã§ä¸¦åˆ—化ã§ãã‚‹)．実装㯠Mahout．ãŸã 最近ã¯ï¼Œãƒãƒƒãƒã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ ã§è§£ã‘ã‚‹å•é¡Œã«ã¯å¤šãã®å ´åˆå¯¾å¿œã™ã‚‹ã‚ªãƒ³ãƒ©ã‚¤ãƒ³ã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ ãŒæ案ã•ã‚Œã¦ã„ã¦ï¼Œãƒãƒƒãƒã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ を並列化ã™ã‚‹ã“ã¨ã®ãƒ¡ãƒªãƒƒãƒˆã¯ã‚ã¾ã‚Šç„¡ã„．オンラインアルゴリズムã ã¨ãƒ‘ラメタãŒé€£ç¶šçš„ã«æ›´æ–°ã•ã‚Œã‚‹ã®ã§ï¼ŒMapR
Type based MCMC: mots quotidiens.
Percy Liang ã® "Type-Based MCMC" (NAACL 2010) [PDF] を何回ã‹ã«åˆ†ã‘ã¦èªã‚“ã§ã„ã¦, よã†ã‚„ãã»ã¼ç†è§£ã§ããŸã€‚ ã“ã‚Œã¯ã™ã”ã„è«–æ–‡ã§ã™ã€‚éžå¸¸ã«åŸºç¤Žçš„ãªè©±ã§, 統計ã®å°‚門ジャーナルã«ã‚‚余裕㧠通る話ã ã¨æ€ã„ã¾ã—ãŸãŒ, NAACLã¨ã„ã†ã€‚Michael JordanãŒç¬¬2(第3ã§ãªã)著者ãªã®ã§, æらã Jordan ã®ãƒ†ã‚¤ã‚¹ãƒˆãŒçµæ§‹å…¥ã£ã¦ã„ã‚‹ã®ã ã¨æ€ã„ã¾ã™ã€‚ よãã“ã‚Œã ã‘ã®å†…容を8ページã«æ›¸ã„ãŸãªã..ã¨ã„ã†ã®ãŒæœ€åˆã®æ„Ÿæƒ³ã§, ã¡ãªã¿ã«, ã‹ãªã‚Šãƒ™ã‚¤ã‚ºçš„ãªè°è«–ã«æ…£ã‚Œã¦ã„ãªã„ã¨, 普通ã®è‡ªç„¶è¨€èªžå‡¦ç†ã®äººã ã¨ãã‚‚ãも何を 言ã£ã¦ã„ã‚‹ã®ã‹ã•ã£ã±ã‚Šã‚ã‹ã‚‰ãªã„ã‹ã‚‚知れãªã„ã¨æ€ã„ã¾ã—ãŸã€‚ å°‘ã—å‰ã«æƒ…処論文誌ã§ãƒˆãƒ³ãƒ‡ãƒ¢æŸ»èªã‚’ã•ã‚Œã¦å”–然ã¨ã—ãŸã®ã§, 余計ã«ãã†æ€ã†ã®ã‹ã‚‚ã—ã‚Œã¾ã›ã‚“ãŒ..。 *1 内部ã®ãƒ™ã‚¤ã‚ºå‹‰å¼·ä¼šã§ã¯åˆ¥ã®è©± ("Painless Unsuperv
NAACL 2010 Retrospective
my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) I just returned from NAACL 2010, which was simultaneously located in my home town of Los Angeles and located nowhere near my home town of Los Angeles. (That's me trying to deride downtown LA as being nothing like real LA.) Overall I was pl
NAACL HLT 2010 - Los Angeles, CA
Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions Michael Heilman and Noah A. Smith Good Question! Statistical Ranking for Question Generation Michael Heilman and Noah A. Smith Unsupervised Modeling of Twitter Conversations Alan Ritter, Colin Cherry and Bill Dolan The viability of web-derived polarity lexicons Leonid Velikovich, Sasha Blair-Goldensohn, Ker
NL Generation: A new problem
my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) Those who talk to me a lot over the years know that I really think that generation is a cool and interesting problem, but one that is hampered by a lack of clarity of what it is, or at least what the input/output is. It's like the problem
NAACL-HLT 2009 Retrospective
my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) I hope this post will be a small impetus to get other people to post comments about papers they saw at NAACL (and associated workshops) that they really liked. As usual, I stayed for the whole conference, plus workshops. As usual, I also h
NAACL/HLT 2009å ±å‘Š - DO++
コãƒãƒ©ãƒ‰ãƒ»ãƒœãƒ«ãƒ‰ãƒ¼ã§é–‹å‚¬ã•ã‚ŒãŸNAACL/HLT 2009ã«è¡Œã£ã¦ãã¾ã—ãŸã€‚ NAACLã¯è‡ªåˆ†ã®ä¸ã§ã®åˆ†é¡žã§ã¯è‡ªç„¶è¨€èªžå‡¦ç†ã®å¦ä¼šã§çµ±è¨ˆçš„ãªæ‰‹æ³•ã¨ã‹ãŒå¤šã„å¦ä¼šã«æ€ãˆã‚‹ï¼ˆãã‚Œã«å¯¾ã—ヨーãƒãƒƒãƒ‘ã§ã¯EACLã§ã¯æ–‡æ³•ã¨ã‹è¨€èªžç†è«–ã¨ã‹ãŒå¤šã„）。比較的自分ã«ã‚ã†å¦ä¼šã€‚ 開催地ã¨ãªã£ãŸã‚³ãƒãƒ©ãƒ‰å¤§ãƒœãƒ«ãƒ€ãƒ¼æ ¡ã¯ã¨ã¦ã‚‚ãã‚Œã„ãªã‚ャンパスã§ï¼ˆã€ã€Œå…¨ç±³ã§æœ€ã‚‚美ã—ã„ã‚ャンパスã€ã®4ä½ã«ãƒ©ãƒ³ã‚ング）ã€å®‡å®™é£›è¡Œå£«ã‚’ãŸãã•ã‚“輩出ã—ã¦ãŸã‚Šã€ãƒŽãƒ¼ãƒ™ãƒ«ç‰©ç†å¦è³žã‚’ï¼”å輩出ã™ã‚‹ãªã©ã€ç ”究レベルも高ã„ãã†ã§ã™ã€‚ ã§ã€å¦ä¼šã¯é©å½“ã«ä¼‘ã¿ãªãŒã‚‰ã¾ã£ãŸã‚Šèžã„ã¦ã„ãŸã®ã§ã™ãŒå…¨ä½“çš„ã«æ•™å¸«ç„¡å¦ç¿’ã«é–¢ã™ã‚‹è©±ãŒå¤šã‹ã£ãŸã‚ˆã†ãªæ°—ãŒã—ã¾ã™ã€‚教師有å¦ç¿’ã«ã‚ˆã‚‹è¨€èªžå‡¦ç†ãŒã‚る程度æˆç†Ÿã—ã¦ãã¦ã„ã‚‹ã®ã«å¯¾ã—ã€æ•™å¸«ç„¡ã®æ–¹ã¯ã¾ã ã¾ã 伸ã³ã—ã‚ãŒå¤šã„ã®ã§ç ”究ãŒã—ã‚„ã™ã„ã®ã§ã—ょã†ã€‚教師無ã«åˆ©ç”¨ã™ã‚‹ãƒ¢ãƒ‡ãƒ«ã‚‚ã€å˜ç´”ãªæ··åˆåˆ†å¸ƒã‹ã‚‰ã€æ§˜ã€…ãªåˆ†å¸ƒãŒå…¥ã‚Šä¹±ã‚Œã‚‹è¤‡é›‘ãªã‚°ãƒ©ãƒ•ã‚£ã‚«ãƒ«ãƒ¢ãƒ‡ãƒ«ã«ãª
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
NAACL HLT 2010 - Los Angeles, CA
{{#tags}}- {{label}}
{{/tags}}