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
対話システム
Search
Yumeto Inaoka
March 30, 2017
Technology
0
78
対話システム
2017/03/30のB3ゼミで発表
Yumeto Inaoka
March 30, 2017
Tweet
Share
More Decks by Yumeto Inaoka
See All by Yumeto Inaoka
文献紹介: Quantity doesn’t buy quality syntax with neural language models
yumeto
1
130
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
170
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
120
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
120
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
93
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
210
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
270
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
180
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
180
Other Decks in Technology
See All in Technology
ISUCONに強くなるかもしれない日々の過ごしかた/Findy ISUCON 2024-11-14
fujiwara3
8
870
OCI Security サービス 概要
oracle4engineer
PRO
0
6.5k
BLADE: An Attempt to Automate Penetration Testing Using Autonomous AI Agents
bbrbbq
0
300
障害対応指揮の意思決定と情報共有における価値観 / Waroom Meetup #2
arthur1
5
470
Engineer Career Talk
lycorp_recruit_jp
0
170
初心者向けAWS Securityの勉強会mini Security-JAWSを9ヶ月ぐらい実施してきての近況
cmusudakeisuke
0
120
マルチプロダクトな開発組織で 「開発生産性」に向き合うために試みたこと / Improving Multi-Product Dev Productivity
sugamasao
1
300
生成AIが変えるデータ分析の全体像
ishikawa_satoru
0
100
[CV勉強会@関東 ECCV2024 読み会] オンラインマッピング x トラッキング MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping (Chen+, ECCV24)
abemii
0
220
VideoMamba: State Space Model for Efficient Video Understanding
chou500
0
190
【Startup CTO of the Year 2024 / Audience Award】アセンド取締役CTO 丹羽健
niwatakeru
0
1k
なぜ今 AI Agent なのか _近藤憲児
kenjikondobai
4
1.4k
Featured
See All Featured
The Power of CSS Pseudo Elements
geoffreycrofte
73
5.3k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
720
Navigating Team Friction
lara
183
14k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
93
16k
How GitHub (no longer) Works
holman
310
140k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
Practical Orchestrator
shlominoach
186
10k
Optimising Largest Contentful Paint
csswizardry
33
2.9k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
250
21k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
6
410
The MySQL Ecosystem @ GitHub 2015
samlambert
250
12k
Git: the NoSQL Database
bkeepers
PRO
427
64k
Transcript
ରγεςϜ #θϛ ࣗવݴޠॲཧݚڀࣨɹҴԬເਓ
ࢀߟʹͨ͠ॻ੶
ൃද༰ ˗ ରγεςϜͷྺ࢙ ˗ ൃʹ͍ͭͯ ˗ ձͷެཧ ˗ ࣭Ԡ ˗
Ԡੜͷݚڀ
ൃද༰ ˗ ରγεςϜͷྺ࢙ ˗ ൃʹ͍ͭͯ ˗ ձͷެཧ ˗ ࣭Ԡ ˗
Ԡੜͷݚڀ
ରγεςϜͷྺ࢙ ˗ &-*;" ˗ 4)3%-6 ˗
"5*4 ˗ 4JSJ
&-*;" ˗ ਫ਼ਆྍ๏ʹ͓͚ΔΧϯηϦϯάΛ฿ ˗ ରऀͷൃͷதΛཧղ͠ͳ͍ ˗ ϧʔϧΛ༻͍ͯରΛଓ͚Δ ྫ ൃʹBMXBZTΛؚΉ ˠl4IPXNFTPNFTQFDJpDFYBNQMFTz
˗ Λݶఆ͠ͳ͍ɿΦʔϓϯυϝΠϯ ˗ ඪΛ࣋ͨͳ͍ɿඇλεΫࢦܕରγεςϜ
4)3%-6 ˗ ϩϘοτΞʔϜʹΑΔੵΈͷૢ࡞ʹݶఆ ˗ ཧղʹجͮ͘ର ˗ ঢ়ଶมԽΛѲ ˗ রԠදݱΛղऍ ˗
Λݶఆ͢ΔɿΫϩʔζυυϝΠϯ ˗ ඪΛ࣋ͭɿλεΫࢦܗରγεςϜ
"5*4 ˗ ϑϥΠτใҊ ˗ ԻʹΑΔର Իೝࣝɺݴޠཧղ ˗ Λݶఆ͢ΔɿΫϩʔζυυϝΠϯ ˗
ඪΛ࣋ͭɿλεΫࢦܗରγεςϜ
4JSJ ˗ ܞଳૢ࡞ɺ࣭ԠΛߦ͏αʔϏε ˗ &-*;"ܕͷࡶஊର͕༥߹ ˗ ԻʹΑΔର
ൃද༰ ˗ ରγεςϜͷྺ࢙ ˗ ൃʹ͍ͭͯ ˗ ձͷެཧ ˗ ࣭Ԡ ˗
Ԡੜͷݚڀ
ൃͷҙຯ ˗ ࣄଶͷදݱ͚ͩͰͳ͘ɺ ฉ͖खͷಇ͖͔͚ɺҙࢥͷද໌ ˗ ґཔɺק༠ɺ໋ྩɺଋɺએݴͳͲ ྫ ༵ՋͰ͔͢ʁˠ༵ʹ༡΅͏ ק༠
ͪΐͬͱॵ͍ͶˠΤΞίϯΛೖΕͯ ґཔ
ൃͷҙຯ ˗ ࣈ໘Ҏ্ͷؒతͳҙຯΛୡ͢ΔߦҝΛ ؒൃߦҝͱΑͿ ˗ ؔઅൃߦҝ͕දؒ͢తͳҙຯΛ ձͷؚҙͱΑͿ ͪΐͬͱॵ͍Ͷɹؒൃߦҝ ΤΞίϯΛೖΕͯձͷؚҙ
ൃʹ͍ͭͯ ˗ ൃจ຺ͷґଘ͕େ͖͍ ˠจ຺͔ΒΓͯ͠ҙຯΛߟ͑Δ ɹ͜ͱ͕Ͱ͖ͳ͍ ˗ จ຺ʹجͮ͘ൃͷҙຯΛѻ͏Λ ޠ༻ͱΑͿ
ൃද༰ ˗ ରγεςϜͷྺ࢙ ˗ ൃʹ͍ͭͯ ˗ ձͷެཧ ˗ ࣭Ԡ ˗
Ԡੜͷݚڀ
ձͷެཧ ྔͷެཧɹɹɿඞཁ͔ͭेͳใΛఏࣔ ࣭ͷެཧɹɹɿਅ࣮ੑͷ͋ΔใΛఏࣔ ؔੑͷެཧɿؔ࿈ੑͷ͋ΔใΛܝࣔ ༷ࣜͷެཧɹɿ໌֬Ͱ؆ܿͳܗͰใΛܝࣔ ͭͷݪཧΛ·ͱΊͯձͷެཧͱΑͿ ͜ͷެཧʹج͍ͮͯձ͕ߦΘΕΔ͜ͱΛ ڠௐݪཧͱΑͿ
ձͷެཧ ˗ ձձͷެཧΛຬͨ͢ ˗ Ұݟެཧʹ͢ΔͱࢥΘΕΔൃʹ ཧ༝͕͋Δͱߟ͑Δ ༵ՋͰ͔͢ʁˠ݄༵ʹࢼݧ͕͋Δɻ ˢ࣭ʹ͍͑ͯͳ͍͕ɺק༠Λஅ͍ͬͯΔ
ൃද༰ ˗ ରγεςϜͷྺ࢙ ˗ ൃʹ͍ͭͯ ˗ ձͷެཧ ˗ ࣭Ԡ ˗
Ԡੜͷݚڀ
࣭Ԡ ࣭ɿʮ࢜ࢁͷߴ͞ԿϝʔτϧͰ͔͢ʁʯ ˗ ࣭ʹରͯ͑͠Λ໌֬ʹநग़ͯ͑͠Δ ˗ ۩ମతͳࣄ࣮Λ͏࣭ɿࣄ࣮ܕ࣭ ࣭จ͔ΒճͷλΠϓΛਪఆ ࣭ΛΫΤϦͱͯ͠ใݕࡧ
ճީิͷநग़ සग़ݱจ຺ͰϥϯΩϯάΛߦ͏ ˗ *#.ͷ8BUTPOʹ࣮
ൃද༰ ˗ ରγεςϜͷྺ࢙ ˗ ൃʹ͍ͭͯ ˗ ձͷެཧ ˗ ࣭Ԡ ˗
Ԡੜͷݚڀ
Ԡੜͷݚڀ ˗ FODPEFSEFDPEFSϞσϧΛ༻͍ͨԠੜ ͷݚڀ͕ߦΘΕ͍ͯΔ ˗ FODPEFSͰೖྗൃΛ୯ޠͣͭಡΈࠐΉ ˗ EFDPEFSͰ୯ޠͣͭԠΛग़ྗ ˗ ྲྀெͳจ͕ੜՄೳ
ൃදͨ͠༰ ˗ ରγεςϜͷྺ࢙ ˗ ൃʹ͍ͭͯ ˗ ձͷެཧ ˗ ࣭Ԡ ˗
Ԡੜͷݚڀ