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
日本語の語彙平易化
Search
moguranosenshi
August 11, 2014
Research
170
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
日本語の語彙平易化
moguranosenshi
August 11, 2014
More Decks by moguranosenshi
See All by moguranosenshi
ベクトル空間における単語表現の効率的推定
moguranosenshi
0
150
自己PR(2013.11.30)
moguranosenshi
0
540
Other Decks in Research
See All in Research
クラウド・AI 時代の研究開発 DX / R&D Digital Transformation
hariby
0
140
SLAMはどこまで解決されたのか?
tomonom
0
1.3k
[BlackHatAsia2026] Hidden Telemetry: Uncovering TraceLogging ETW Providers You're Not Using (Yet)
asuna_jp
1
700
データサイエンティストの就労意識~2015 → 2026 一般(個人)会員アンケートより
datascientistsociety
PRO
0
760
JICA QUEST 共創×革新プログラム Impact Report(海ノ向こうコーヒー)
ontheslope
0
540
【中間報告】国会議員の立法・政策実務を支える環境を巡る現状と課題
polipoli
0
570
全国町字単位空き家率推定データver1.0データ仕様
microbaseinc
0
220
最先端NLP 2026 論文紹介: Wait, Wait, Wait... Why Do Reasoning Models Loop? / SNLP Paper Review: Wait, Wait, Wait... Why Do Reasoning Models Loop?
tkng
0
220
長時間動画QAにおけるマルチエージェント推論 ・SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
murakawatakuya
1
200
論文紹介: Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind
hisaokatsumi
0
160
高性能計算機クラスタを用いた大規模点群処理による森林の単木抽出と構造解析
kentaitakura
1
120
Model Discovery and Graph Simulation: A Lightweight Gateway to Chaos Engineering
anatolykr
0
300
Featured
See All Featured
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
16k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
520
Design of three-dimensional binary manipulators for pick-and-place task avoiding obstacles (IECON2024)
konakalab
0
580
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Visualization
eitanlees
152
17k
DevOps and Value Stream Thinking: Enabling flow, efficiency and business value
helenjbeal
1
380
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
2.1k
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
2
500
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
74
42k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
21
1.6k
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
1
520
GraphQLとの向き合い方2022年版
quramy
50
15k
Transcript
ຊޠͷޠኮฏқԽ Ԭٕज़Պֶେֶ म࢜̎ɹֿݪஐ೭
ࣗݾհ • Ԭٕज़Պֶେֶిؾిࢠใֶઐ߈ – ߴઐੜ͕ฤೖֶ͢ΔͨΊͷେֶ – ׂ̔ͷֶੜֶ͕෦͔̏Βฤೖֶ – ଔॻ͔ͣɺ#̐Ͱ̑ϲ݄ؒͷΠϯλʔϯ –
ֿݪɿ৽ډߴઐʢѪඤݝʣ͔Βฤೖֶ • ࣗવݴޠॲཧݚڀࣨʢIUUQXXXKOMQPSHʣ – ।ڭतɺम࢜̑ਓɺֶ෦̏ਓ – ܗଶૉղੳɺຊޠߍਖ਼ɺςΩετฏқԽ – ֿݪɿࢠͲ͚ͷޠኮฏқԽΛݚڀ
ݚڀͷഎܠ େྔɾଟ༷ͳςΩετσʔλ ΞΫηε༰қ ཧղ༰қʁ ࢠڙ େਓ ֎ࠃਓ ߴྸऀ
ݚڀͷഎܠ େྔɾଟ༷ͳςΩετσʔλ ΞΫηε༰қ ཧղ༰қʁ ࢠڙ େਓ ֎ࠃਓ ߴྸऀ ޮతͳใऩूɾࣝ֫ಘͷͨΊ
ݴޠೳྗͷࠩΛຒΊΔٕज़͕ඞཁ จষಡղࢧԉͷͨΊͷޠኮฏқԽ
ޠኮͷฏқԽ ̍ ฏқͳޠኮͷબఆʢֶशجຊޠኮʣ ̎ ղͳޠΛฏқͳޠኮதͷޠݴ ൃ ࣙ ىૌ େਓ͚ޠኮ
৽ฉؒ૯ޠኮ ສޠ ࢝ΊΔ ΊΔ ͏ͬͨ͑Δ ࢠͲ͚ޠኮ ֶशجຊޠኮ ޠ ݴ ,FZXPSE -FYJDBM 4JNQMJpDBUJPO -FYJDBM 1BSBQISBTJOH
ࣝʹجͮ͘ޠኮతݴ ຊޠɿओཁ෦ऴܕݴޠ ࠃޠࣙయΛ༻͍ͨ ޠኮతݴͷநग़ ࣮ݧɿޠ ฏқԽͰ͖Δޠͷׂ߹ খֶࠃޠࣙయͷΈ ෳͷݴࣝΛซ༻
࣮ݧɿจ ཧղͰ͖Δจͷׂ߹ ฏқԽલ ฏқԽޙ ˞ޠΛ̍ޠؚ͚ͩΉ৽ฉهࣄͰ࣮ݧ ˞খֶߴֶͷඃݧऀ໊̑ʹΑΔධՁ
ޠͷฏқԽͷධՁ • σʔλɿͷຖ৽ฉʹසग़͢Δޠޠ ɹɹɹɹͦΕΒΛຊख๏Ͱݴͨ͠ฏқޠޠ • ඃݧऀɿখֶ̑ੜ̎ਓɺ̒ੜ̏ਓͷܭ̑ਓ • ޠ͔ฏқޠ͔Λ͑ͣɺϥϯμϜʹޠΛఏࣔ •
ඃݧऀ֤ޠʹ͍ͭͯɺ˓PS✕Ͱճ – ˓ɿͦͷޠͷҙຯ͕͖ͬΓ͔Δ – ºɿͦͷޠͷҙຯ͕ᐆດͰ͋Δ͔ɺ͔ͯ͘͠Βͳ͍ ޠ ฏқޠ ඃݧऀͷখֶੜߴֶ̑ਓͷ͏ͪ ̏ਓҎ্͕ཧղͰ͖Δޠͷׂ߹
ݴʹΑΔจͷฏқԽͷධՁ ݴޙɺฏۉͷจΛখֶੜ͕ཧղ͢Δ͜ͱ͕Ͱ͖Δ ฏۉͷจɺݴޙͷํ͕қ͕Լ͕͍ͬͯΔ 78 50 75 43
78 93 56 91 71 85 65 59 64 63 68 0 10 20 30 40 50 60 70 80 90 100 被験者1 被験者2 被験者3 被験者4 被験者5 換言前の文を理解可能 換言後の文を理解可能 難しい → 易しい
༻ྫʹجͮ͘ޠኮతݴ TJN OU OD DPN OU OD MPH
/WBS OD ɹOU ɿݴରͷ໊ࢺɺɹOD ɿݴީิͷ໊ࢺ ɹDPN OU OD ɿOU ͱOD ͕ڞ௨ͯ͠༻͍ΒΕΔจ຺ͷछྨ ɹ/ɿจ຺ͷ૯ɺ WBS OD ɿOD ͕༻͍ΒΕΔจ຺ͷछྨ
ؔ࿈ख๏ͱൺֱ • ίʔύε͔Βจ຺Λݟͯݴ͢Δख๏ͱൺֱ • ಛϕΫτϧͷ༨ݭྨࣅ͕ߴ͍ޠݴ͢Δ • <.BSUPO> – จ຺ͷޠͱͷڞىසͰಛϕΫτϧΛੜ –
ଟ͘ڞى͢Δจ຺ͷӨڹ͕େ͖͍ • <#IBHBU> – จ຺ͷޠͱͷࣗݾ૬ޓใྔͰಛϕΫτϧΛੜ – ภͬͯڞى͢Δจ຺ͷӨڹ͕େ͖͍
ݴՄೳͳ໊ࢺʢྨࣅ̍Ґʣ
ධՁऀ" ධՁऀ# ධՁऀ$ ఏҊख๏ <.BSUPO> <#IBHBU> จ຺ͷग़ݱසʹґଘ͠ͳ͍ఏҊख๏͕࠷༏Ε͍ͯΔ ˞શޠ ʦޠʧ
ධՁऀ" ධՁऀ# ධՁऀ$
ఏҊख๏ <.BSUPO> <#IBHBU> ݴՄೳͳ໊ࢺʢྨࣅ্ҐҐʣ Ґ·ͰݟΔͱ<#IBHBU>͕ఏҊख๏ʹ͍͍ۙͮͯΔ ˞શޠ ʦޠʧ
ྨࣅͱݴՄೳͳ໊ࢺ Ґ Ґ Ґ
Ґ Ґ Ґ Ґ Ґ Ґ Ґ ධՁऀ" ఏҊख๏ <.BSUPO> <#IBHBU> ఏҊख๏ ̍Ґͱ̎Ґͷ͕ࠩେ͖͍ #IBHBU̍Ґͱ̎Ґͷ͕ࠩখ͍͞ ɹˠɹఏҊख๏ͷ੍ ɹɹɹɹɹʮೖྗͱಉ͡จ຺Ͱ༻͍ΒΕΔ໊ࢺʹݴ͢Δʯ ˞શޠ ʦޠʧ
จ຺Λߟྀͨ͠ݴࣄྫ • ʙສԁҎԼͷʲേۚʳʹॲ͢Δ • ൺֱख๏ɿɺՊྉɺաྉɺɾɾɾ • ఏҊख๏ɿേۚܐɺաྉɺɾɾɾ • ࠊͷʲෛ୲ʳΛܰݮ͢Δ •
ൺֱख๏ɿඅ༻ɺܦඅɺ࣮අɺɾɾɾ • ఏҊख๏ɿෛՙɺετϨεɺμϝʔδɺɾɾɾ