Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
B3_Seminar_07
Search
kakubari
March 30, 2017
Technology
0
65
B3_Seminar_07
長岡技術科学大学
自然言語処理研究室
角張竜晴
kakubari
March 30, 2017
Tweet
Share
More Decks by kakubari
See All by kakubari
動詞クエリの語間の関係性に基づくクエリマイニング
kakubari
0
110
Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis
kakubari
1
160
Leveraging Crowdsourcing for Paraphrase Recognition
kakubari
0
82
Automatically Acquired Lexical Knowledge Improves Japanese Joint Morphological and Dependency Analysis
kakubari
0
100
Labeling the Semantic Roles of Commas
kakubari
0
76
Integrating Case Frame into Japanese to Chinese Hierarchical Phrase-based Translation Model
kakubari
0
110
Improving Chinese Semantic Role Labelingusing High-quality Surface and Deep Case Frames
kakubari
0
89
Exploring Verb Frames for Sentence Simplification in Hindi
kakubari
0
130
述語項構造と照応関係のアノテーション
kakubari
0
230
Other Decks in Technology
See All in Technology
LLM時代のパフォーマンスチューニング:MongoDB運用で試したコンテキスト活用の工夫
ishikawa_pro
0
160
Generative AI Japan 第一回生成AI実践研究会「AI駆動開発の現在地──ブレイクスルーの鍵を握るのはデータ領域」
shisyu_gaku
0
310
まずはマネコンでちゃちゃっと作ってから、それをCDKにしてみよか。
yamada_r
2
120
20250913_JAWS_sysad_kobe
takuyay0ne
2
240
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
10
75k
Autonomous Database - Dedicated 技術詳細 / adb-d_technical_detail_jp
oracle4engineer
PRO
4
10k
Codeful Serverless / 一人運用でもやり抜く力
_kensh
7
450
初めてAWSを使うときのセキュリティ覚書〜初心者支部編〜
cmusudakeisuke
1
270
20250910_障害注入から効率的復旧へ_カオスエンジニアリング_生成AIで考えるAWS障害対応.pdf
sh_fk2
3
260
現場で効くClaude Code ─ 最新動向と企業導入
takaakikakei
1
260
DroidKaigi 2025 Androidエンジニアとしてのキャリア
mhidaka
2
370
Firestore → Spanner 移行 を成功させた段階的移行プロセス
athug
1
490
Featured
See All Featured
Art, The Web, and Tiny UX
lynnandtonic
303
21k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
How STYLIGHT went responsive
nonsquared
100
5.8k
Code Reviewing Like a Champion
maltzj
525
40k
Git: the NoSQL Database
bkeepers
PRO
431
66k
Into the Great Unknown - MozCon
thekraken
40
2k
Building an army of robots
kneath
306
46k
Building a Modern Day E-commerce SEO Strategy
aleyda
43
7.6k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
252
21k
VelocityConf: Rendering Performance Case Studies
addyosmani
332
24k
What's in a price? How to price your products and services
michaelherold
246
12k
Side Projects
sachag
455
43k
Transcript
Ԭٕज़Պֶେֶ ిؾిࢠใֶ՝ఔ ֶ෦ɹ֯ுཽ ࣗવݴޠݚڀࣨ ɹ#̏θϛ ʙୈճʙ ใΞΫηεධՁํ๏ᶄ 1
今日の内容 ˔جຊతͳใݕࡧධՁࢦඪ ɹɾٯॱҐ ˔ςΩετΛରͱͨ͠ใΞΫηεධՁ ɹɾ#-&6 2
Web検索の検索意図 ˔#SPEFS͕ʹࣔͨ͠ݕࡧҙਤͷ̏ͭͷλΠϓ ɾ༠ಋܕ ಛఆͷαΠτΛ๚Ε͍ͨͱ͍͏ҙਤ ɾใऩूܕ ҰͭҎ্ͷΣϒϖʔδʹॻ͔Ε͍ͯΔͱࢥΘΕΔ ใΛऔಘ͍ͨ͠ͱ͍͏ҙਤ ɾऔҾܕ ΣϒΛհͱͨ͠ΞΫγϣϯΛ࣮ߦ͍ͨ͠ͱ͍͏ ҙਤʢྫ͑ɺҿ৯ళͷ༧ʣ
3
逆数順位 ˔༠ಋܕݕࡧҙਤʹదͨ͠ධՁࢦඪ ɹɾಛఆͷαΠτΛ๚Ε͍ͨ ɹɾཉ͍͠จॻΛҰͭݟ͚͍ͭͨ ˔ٯॱҐͷఆٛ ɹݕࡧ݁Ռதɺ࠷্Ґͷద߹จॻͷϥϯΫΛS ͱ͠ɺ ద߹จॻΛؚ·ͳ͍߹ʹɺಛʹS
ʹ㱣ͱ͢Δɻ ͜ͷ࣌ͷٯॱҐ SFDJQSPDBMSBOL ɺ ಛʹɺݕࡧ݁Ռ͕ద߹จॻΛؚ·ͳ͍߹33 RR= 1 r 1 4
テキストを対象とした情報アクセス評価指標 ˔ػց༁ͷࣗಈධՁࢦඪɹ#-&6 ɹػց༁ͷࣗಈධՁͰɺਓखʹΑΔෳͷਖ਼ղ σʔλʢଈͪࢀর༁ʣΛ༩͑Δඞཁ͕͋Δɻ ɹ༁ͷํҰ௨ΓͰͳ͍ͨΊ
5
BLEU ࢀর༁T ɿ5IFDBUJTPOUIFNBU ʢୈҰͷࢀর༁ʣ ɹɹɹT ɿ5IFSFJTBDBUPOUIFNBUʢୈೋͷࢀর༁ʣ ධՁͷରͱͳΔػց༁ͷ݁ՌɿT
5IFNBUJTPOUIFDBU ͜ͷจTʹؚ·ΕΔશϢχάϥϜ HSBN T \lUIFz lNBUz lJTz lPOz lDBUz^ ྫ͑ɺzUIFzͷසͰ͋Γɺ ͜ΕΛ$ lUIFz ͷΑ͏ʹද͢ɻ 6
BLEU ಉ༷ʹɺTʹରԠ͢ΔୈҰͷࢀর༁T Ͱ $ lUIFz T
ୈೋͷࢀর༁T ʹ͍ͭͯ $ lUIFz T ػց༁ͷ݁Ռͷ֤จTΛධՁ͢Δʹɺ ࢀর༁தͰ͜ΕʹରԠ͢Δਖ਼ղ༁ͱͷۙ͞Λߟ͑Δɻ 7
BLEU Ұͭͷख͕͔Γͱͯ͠ɺ ਖ਼ղ༁ͱػց༁݁Ռͷ྆ํʹؚ·ΕΔzUIFzͷΑ͏ ͳϢχάϥϜͷසʹ͍ͭͯൺֱ͢Δɻ ྫ͑ʜ ػց༁݁ՌʹzUIFz͕ճग़ݱ͍ͯͯ͠ɺ ୈҰͷࢀর༁ʹ̎ճɺୈೋͷࢀর༁ʹ̍ճ͔͠ग़ ݱ͠ͳ͍ɻ ػց༁݁ՌʹճͷใुΛ༩͑ͳ͍ɻ
8
BLEU ैͬͯɺHSBN T HSBN T ͕ͱʹؚΉ֤Ϣχά ϥϜFʹ͍ͭͯɺසΛמΓࠐΉ
$MJQ ɻ $MJQ F T NJO NBY $ F T $ F T ྫ͑ɺ$ lUIFz T Ͱ͋ͬͯɺ ɹɹɹ$ lUIFz T Ͱ͋Εɺ $MJQ lUIFz T ̎ 9
BLEU ɹಉ༷ʹόΠάϥϜʹ͍ͭͯߟ͍͑ͯ͘ɻ ػց༁Tʹ͍ͭͯ HSBN T \lUIFNBUz lNBUJTz lJTPOz lPOUIFz
lUIFDBUz^ ͱͳΔɻ ɹҎ্ΑΓɺਖ਼ղ༁ʹؚ·Εͳ͍zNBUJTz͕ଘࡏ͢Δ ͜ͱ͕Θ͔ΓɺϢχάϥϜΑΓࡉ͔͍ධՁͰ͖Δɻ /άϥϜͰɺΑΓࡉ͔͍ධՁ͕Ͱ͖Δ 10
BLEU ػց༁݁ՌશମʢจTͷू߹ʣͷධՁΛߦ͏ࡍɺ /άϥϜͷמΓࠐΈසʹجͮ͘ࢦඪΛߟ͑Δɻ 1SFD / ɺਫ਼ʹ֤/άϥϜͷසΛಋೖͨ͠ͷʹ
૬͢Δɻ Prec N = Clip(e,s) e∈gramN (s) ∑ s ∑ C(e,s) e∈gramN (s) ∑ s ∑ 11
BLEU #-&6Ͱɺ͞Βʹ/ ʹ͍ͭͯ1SFD/ ΛҎԼ ͷΑ͏ʹ݁߹͢Δɻ
͜Εਫ਼ʹࣅͨࢦඪͷͨΊɺػց༁݁Ռʹؚ·Ε ΔϊΠζʹରͯ͠ϖφϧςΟΛ༩͑Δ͜ͱ͕Ͱ͖Δɻ PREC = exp( 1 4 lnPrec N N∈{1,2,3,4} ∑ ) 12
BLEU ˔ϖφϧςΟΛ༩͑Δج४ ػց༁݁Ռ͕ୈҰͷਖ਼ղ༁ͱશͯҰகͨ͠߹ɺ ୈೋͷਖ਼ղ༁ͷzUIFSFzΛؚ·ͳ͍͔ΒϖφϧςΟΛ ༩͑Δ͜ͱෆదɻ /άϥϜͷ࠶ݱΛߟ͑ΔΘΓʹɺ ɹػց༁݁Ռͷ͞ʹண 13
BLEU ػց༁݁Ռͷ͕͞ਖ਼ղ༁ͷ͞ͱൺֱͯ͠ʜ ᶃ͗͢Δͱஅͨ͠߹ ɹϖφϧςΟΛ༩͑Δ ᶄ͗͢Δͱஅͨ͠߹ ɹ13&$ʹΑΓϖφϧςΟ͕༩͑ΒΕΔ 14
BLEU ػց༁݁Ռதͷ֤จTʹ͍ͭͯɺରԠ͢Δਖ਼ղจT ͷ͏͕ͪ͞࠷Tʹ͍ۙͷΛબɻ ͦͷਖ਼ղจͷ͞Λ ࠷దϚονɿ#.- T Ͱද͢ɻ ͦͯ͠ɺػց༁݁Ռશମʹ͍ͭͯͦͷΛٻΊΔͱ
4#.-ػց༁݁Ռͷཧతͳ͞ʹ૬͢Δ SBML = BML(s) = arg len(s* ) min len(s)− len(s* ) s ∑ s ∑ 15
BLEU Ұํɺػց༁݁Ռͷશͷ࣮ଌ ͜ΕΒΑΓɺ#-&6ͷ؆қϖφϧςΟ 4:4-4.#-ͷ࣌ɺ#1ͱͳΓ ϖφϧςΟ͕՝͞ΕΔɻ
SYSL = len(s) s ∑ BP=exp(min(0,1- SBML SYSL )) 16
BLEU Ҏ্ͷఆٛʹج͖ͮɺ#-&6 ˔#-&6ͷ·ͱΊ ɾجຊతʹසΛߟྀͨ͠/άϥϜʹجͮ͘ਫ਼ ɾػց༁݁Ռશମͱͯ͗͢͠Δͱஅͨ͠߹ɺ ɹϖφϧςΟΛ՝͢ࢦඪ
BLEU=BP PREC 17
参考文献 ˔ใΞΫηεධՁํ๏ʢ̏ɺ̐ষʣɺञҪɺ ɹίϩφࣾɺ݄ 18