$30 off During Our Annual Pro Sale. View Details »

言語処理学会第24回年次大会 参加報告

Avatar for Yumeto Inaoka Yumeto Inaoka
March 19, 2018
Research
0
140

言語処理学会第24回年次大会 参加報告

2018/03/19の年次大会報告会で発表

Avatar for Yumeto Inaoka

Yumeto Inaoka

March 19, 2018
Tweet

More Decks by Yumeto Inaoka

See All by Yumeto Inaoka
文献紹介: Quantity doesn’t buy quality syntax with neural language models
Avatar for Yumeto Inaoka yumeto
1
200
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
Avatar for Yumeto Inaoka yumeto
0
250
文献紹介: Self-Supervised_Neural_Machine_Translation
Avatar for Yumeto Inaoka yumeto
0
170
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
Avatar for Yumeto Inaoka yumeto
0
180
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
Avatar for Yumeto Inaoka yumeto
0
170
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
Avatar for Yumeto Inaoka yumeto
0
290
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
Avatar for Yumeto Inaoka yumeto
0
360
文献紹介: Decomposable Neural Paraphrase Generation
Avatar for Yumeto Inaoka yumeto
0
240
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
Avatar for Yumeto Inaoka yumeto
0
240

Other Decks in Research

See All in Research
一人称視点映像解析の最先端（MIRU2025 チュートリアル）
Avatar for Takuma Yagi takumayagi
6
4.4k
CVPR2025論文紹介：Unboxed
Avatar for 村川卓也 murakawatakuya
0
230
第二言語習得研究における 明示的・暗示的知識の再検討：この分類は何に役に立つか，何に役に立たないか
Avatar for Yu Tamura tam07pb915
0
400
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
Avatar for Akihiro Kokubo akihiro_kokubo
PRO
64
35k
[IBIS 2025] 深層基盤モデルのための強化学習 驚きから理論にもとづく納得へ
Avatar for Akifumi Wachi akifumi_wachi
18
8.9k
教師あり学習と強化学習で作る 最強の数学特化LLM
Avatar for Hiroshi Y (RabotniKuma) analokmaus
2
770
Open Gateway 5GC利用への期待と不安
Avatar for Stellar Craft, Inc. stellarcraft
2
170
学習型データ構造：機械学習を内包する新しいデータ構造の設計と解析
Avatar for Yusuke Matsui matsui_528
4
2.2k
MIRU2025 チュートリアル講演「ロボット基盤モデルの最前線」
Avatar for Kento Kawaharazuka haraduka
15
11k
Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping
Avatar for SatAI.challenge satai
3
410
Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
Avatar for SatAI.challenge satai
3
230
令和最新技術で伝統掲示板を再構築: HonoX で作る型安全なスレッドフロート型掲示板 / かろっく@calloc134 - Hono Conference 2025
Avatar for calloc134 calloc134
0
450

Featured

See All Featured
30 Presentation Tips
Avatar for Ian Lurie portentint
PRO
1
170
Money Talks: Using Revenue to Get Sh*t Done
Avatar for Nikki Halliwell nikkihalliwell
0
120
Docker and Python
Avatar for Tania Allard trallard
47
3.7k
The Success of Rails: Ensuring Growth for the Next 100 Years
Avatar for Eileen M. Uchitelle eileencodes
47
7.9k
Code Reviewing Like a Champion
Avatar for maltzj maltzj
527
40k
Navigating Algorithm Shifts & AI Overviews - #SMXNext
Avatar for Aleyda Solis aleyda
0
1k
SEOcharity - Dark patterns in SEO and UX: How to avoid them and build a more ethical web
Avatar for Sara Fernández Carmona sarafernandez
0
83
So, you think you're a good person
Avatar for Per Axbom axbom
PRO
0
1.8k
Build The Right Thing And Hit Your Dates
Avatar for Maggie C. maggiecrowley
38
3k
SEO Brein meetup: CTRL+C is not how to scale international SEO
Avatar for Linda Hogenes lindahogenes
0
2.2k
A brief & incomplete history of 
UX Design for the World Wide Web: 1989–2019
Avatar for Jason CranfordTeague jct
1
260
How People are Using Generative and Agentic AI to Supercharge Their Products, Projects, Services and Value Streams Today
Avatar for Helen Beal helenjbeal
1
77

Transcript

  1. ݴޠॲཧֶձ
 ୈ24ճ೥࣍େձ ࢀՃใࠂ ௕Ԭٕज़Պֶେֶ ࣗવݴޠॲཧݚڀࣨɹҴԬເਓ

  2. ಛʹڵຯΛऒ͔Εͨൃද ड़ޠͷ׆༻৘ใΛ༻͍ͨχϡʔϥϧ೔ӳ຋༁
 ࠇᖒಓر দଜઇࡩ ࢁ؛ॣल খொक ຋༁ਫ਼౓ʹجͮ͘୯ޠΫϥεࣗಈਪఆख๏
 ҆ాܓࢤ ߴҪެҰ ෰෦ݩ

    ΠϥΫϨ΢εύχίε ੴ઒জ෉ দຊҰଇ ੁ୩࢙ত χϡʔϥϧػց຋༁ʹ͓͚Δڞى৘ใΛߟྀͨ͠ޠኮબ୒
 উຢஐ দଜઇࡩ ࢁ؛ॣल খொक

  3. ड़ޠͷ׆༻৘ใΛ༻͍ͨχϡʔϥϧ೔ӳ຋༁ ׆༻৘ใΛड़ޠ͔Β෼཭ͯ͠ޠኮαΠζΛ࡟ݮ
 ྫ ૸Εˠ૸Δ ಈࢺɾ໋ྩܗ ޠኮΧόʔ཰ #-&6ͱ΋ʹ޲্

  4. ड़ޠͷ׆༻৘ใΛ༻͍ͨχϡʔϥϧ೔ӳ຋༁ FODPEFS EFDPEFSͷ͍ͣΕʹ͓͍ͯ΋ద༻Մೳ
 ˠ຋༁Ҏ֎ʹ΋Ԡ༻Մೳ .F$BC͑͋͞Ε͹ग़དྷΔͷͰ؆୯
 ˠಛʹ*1"%JDͳΒ͹׆༻͔Β෮ݩͰ͖Δͱͷ͜ͱ খن໛ͳίʔύεʹ͓͍ͯಛʹޮՌ༗

  5. ຋༁ਫ਼౓ʹجͮ͘୯ޠΫϥεࣗಈਪఆख๏ ୯ޠΫϥεਪఆͷͨΊͷֶशσʔλΛର༁ίʔύε͔ΒಘΔ
 ˡ຋༁ਫ਼౓͕ߴ͘ͳΔΑ͏ͳ୯ޠΫϥεΛ୳͢ ࡞੒ֶͨ͠शσʔλ͔Β$//ʹΑΔ෼ྨثΛߏங͢Δ ෼ྨثΛ༻͍ͨ຋༁Ͱ3*#&4͕޲্

  6. ຋༁ਫ਼౓ʹجͮ͘୯ޠΫϥεࣗಈਪఆख๏ ʮ୯ޠΫϥεʹΑΔ຋༁ਫ਼౓޲্ʯ͔Β
 ʮ຋༁ਫ਼౓͕࠷ߴͳ୯ޠΫϥεΛ୳͢ʯͱ͍͏ٯసͷൃ૝ ର༁ίʔύε͕຋༁λεΫҎ֎ʹ΋ར༻Ͱ͖ΔՄೳੑ
 ˠίʔύεෆ଍ͩͬͨλεΫ΁ͷޫ

  7. χϡʔϥϧػց຋༁ʹ͓͚Δڞى৘ใΛߟྀͨ͠ޠኮબ୒ /.5ͷग़ྗ୯ޠͷީิͱͳΔޠኮαΠζΛݮΒͨ͢Ίͷ
 ޠኮબ୒ख๏ͷఏҊ ڞى৘ใΛ୯ޠͷॏཁ౓ͱͯ͠ॏཁͳ୯ޠΛબ୒
 ˡ)*54ͱ͍͏ΞϧΰϦζϜΛ࢖༻ ग़ྗະ஌ޠτʔΫϯ਺͸্ঢ͢Δ͕#-&6͸޲্

  8. χϡʔϥϧػց຋༁ʹ͓͚Δڞى৘ใΛߟྀͨ͠ޠኮબ୒ ༻͍ͨ)*54ΞϧΰϦζϜ͸8FCϖʔδͷϥϯΩϯάख๏
 ˠݴޠॲཧ෼໺Ҏ֎Ͱ༻͍ΒΕ͍ͯΔΞϧΰϦζϜ͕
 ɹݴޠॲཧʹར༻Ͱ͖Δ͜ͱ΋͋Δ ͋ΒΏΔχϡʔϥϧจੜ੒λεΫʹద༻Ͱ͖Δख๏ ස౓Λجʹબ୒͞Εͨޠኮ΍ਓखͰબ୒͞Εͨޠኮͱͷ
 ൺֱʹ࢖͑Δ͔΋͠Εͳ͍

  9. ൃද಺༰ ड़ޠͷ׆༻৘ใΛ༻͍ͨχϡʔϥϧ೔ӳ຋༁
 ࠇᖒಓر দଜઇࡩ ࢁ؛ॣल খொक ຋༁ਫ਼౓ʹجͮ͘୯ޠΫϥεࣗಈਪఆख๏
 ҆ాܓࢤ ߴҪެҰ ෰෦ݩ

    ΠϥΫϨ΢εύχίε ੴ઒জ෉ দຊҰଇ ੁ୩࢙ত χϡʔϥϧػց຋༁ʹ͓͚Δڞى৘ใΛߟྀͨ͠ޠኮબ୒
 উຢஐ দଜઇࡩ ࢁ؛ॣल খொक