Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Kaggleではじめるデータサイエンス / Ask the Expert: Kaggle

B1cc148711c6a37a5c922b6e72a4ad52?s=47 Shotaro Ishihara
September 11, 2020
Technology
0
270

Kaggleではじめるデータサイエンス / Ask the Expert: Kaggle

Google Cloudのインタビュー企画「Ask the Expert」
https://upura.hatenablog.com/entry/2020/09/10/210400

B1cc148711c6a37a5c922b6e72a4ad52?s=128

Shotaro Ishihara

September 11, 2020
Tweet

More Decks by Shotaro Ishihara

See All by Shotaro Ishihara
Nikkei at SemEval-2022 Task 8: Exploring BERT-based Bi-Encoder Approach for Pairwise Multilingual News Article Similarity
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
10
[Poster] Nikkei at SemEval-2022 Task 8: Exploring BERT-based Bi-Encoder Approach for Pairwise Multilingual News Article Similarity
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
7
新聞記事のクリック率予測に向けたペアワイズ学習用データセットの構築手法の検討 / JSAI2022 Generating Pairwise Dataset for CTR Prediction
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
8
Generating a Pairwise Dataset for Click-through Rate Prediction of News Articles Considering Positions and Contents
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
130
機械学習コンペの近年の潮流 2022 年 4 月版 / ml competition trend 2022.04
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
1k
Editors-in-the-loop なニュース記事要約システムの提案 / Editors-in-the-loop News Article Summarization Framework
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
1.7k
日本経済新聞社における自然言語処理の取り組み / yans2022 nikkei nlp
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
85
Pythonによるアクセスログ解析入門 / Tutorial on Access Log Analysis by Python
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
9
9.6k
Kaggleの魅力と取り組み方 / Attractiveness and Approach of Kaggle
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
630

Other Decks in Technology

See All in Technology
DeFiChain Tech Talk - DFI Uniswap Staking, DeFi Options & DeFi Meta Chain
Cae2dd246ed83dd458e4ce5f927aa2f7?s=48 uzyn
0
100
CityGMLとFBXの連携で地理空間のエンタメ化
A3990cfe49309642cb8d1f50b617c141?s=48 soh_mitian
0
720
フィンテック養成勉強会#24
525442fc70ca92f82ae503f826956137?s=48 finengine
0
330
ECS Fargate+Mackerelにおける監視費用を削減するまでの話
3e77f9dbec6a87756d1dbdddab283aee?s=48 nulabinc
PRO
1
450
年700万円損するサーバレスの 認可システムをご紹介します！！
Fb0a40e5e7a9dc85520f1646fd41eb44?s=48 higuuu
3
330
ソフトウェアアーキテクチャの基礎: Software Architecture in a Nutshell
941b170e5a115a295cccb5f5cdf0a800?s=48 snoozer05
28
8.8k
Oracle Cloud Infrastructure：2022年7月度サービス・アップデート
3115a782126be714b5f94d24073c957d?s=48 oracle4engineer
PRO
0
180
LINSTOR — это как Kubernetes, но для блочных устройств
93aef1d166a8a3536538eff713f80307?s=48 flant
0
2.8k
GCCP Creator @ COSCUP 2022
2102a6b8760bd6f57f672805723dd83a?s=48 line_developers_tw
PRO
0
1.4k
金融領域のマルチプロダクトを効率よく開発・運用するためのシステム基盤と組織設計について / 2022-07-28-multi-product-platform
0251532f4fb413ea1a026efe6eb16b87?s=48 stajima
0
150
AWS CLI でやってみる ~ AWS Hands-on for Beginners ECS ハンズオン ~
8785139c395ce2345ce535822b522dde?s=48 kentosuzuki
1
480
Learning to Solve Hard Minimal Problems
2c88806cbaab6024dc95b9a654c99d86?s=48 takmin
1
340

Featured

See All Featured
Agile that works and the tools we love
462dad0dd24c568a32dcdb0ae895ae1b?s=48 rasmusluckow
319
19k
Designing Experiences People Love
1b75d89772b7eea1f6c89fbf362607d9?s=48 moore
130
22k
The Brand Is Dead. Long Live the Brand.
A415db3ac9e9668acbc1fb36eead84ac?s=48 mthomps
46
2.7k
Why Our Code Smells
20bfe76b3d6105641f879fe45cfc9272?s=48 bkeepers
PRO
324
55k
Web Components: a chance to create the future
E190023b66e2b8aa73a842b106920c93?s=48 zenorocha
303
40k
jQuery: Nuts, Bolts and Bling
9cde37f47e4a800ea081ea42de8d749a?s=48 dougneiner
56
6.4k
Stop Working from a Prison Cell
C1daf20e5c49ff910745198ef9869ac2?s=48 hatefulcrawdad
262
17k
Fashionably flexible responsive web design (full day workshop)
433acaea1012b25d97ae66da9b998dad?s=48 malarkey
396
62k
What's new in Ruby 2.0
7edec06b5435e0dac07a353b2cc26253?s=48 geeforr
335
30k
Designing for Performance
245cee81a9c424266e5e401d844ea881?s=48 lara
597
64k
Design by the Numbers
027d1ebf66cc039a0bd3b55eeadbe75d?s=48 sachag
271
17k
5 minutes of I Can Smell Your CMS
465724d73fe3a92c0879fdfb43a3a6f3?s=48 philhawksworth
196
18k

Transcript

  1. RÔČČĦø䛷䛿䛨䜑䜛 䝕䞊䝍䝃䜲䜶䞁䝇 Œģřđø)ŷŋøLj øŋřøīíøŎʽʽ̶ʾʼʾʼ

  2. Œģřđø)ŷŋøLj䛻䛴䛔䛶 ᪂ᆺ䝁䝻䝘䜴䜲䝹䝇ឤᰁ⑕䛜ᘬ䛝㔠䛸䛺䜚䚸 䜎䛳䛯䛺䛧䛷䜔䛳䛶䛟䜛䝕䝆䝍䝹᫬௦䛻 ᚲせ䛺䛂䝅䝇䝔䝮䜰䞊䜻䝔䜽䝖䜔䜶䞁䝆䝙䜰䛃䜔 䛂䝕䞊䝍䝃䜲䜶䞁䝔䜱䝇䝖䚸%-䜶䞁䝆䝙䜰䛃䛺䛹䚸 䜢ᣍ䛝䚸䛣䜜䛛䜙䛾䝅䝇䝔䝮㛤Ⓨ䛻 ᚲせ䛺ᵝ䚻䛺஦᯶䛻䛴䛔䛶᥈䛳䛶䛔䛝䛯䛔䛸ᛮ䛔䜎䛩䚹 䛣䛣䛻Ⓩሙ䛩䜛䜶䜻䝇䝟䞊䝖䛛䜙䚸䛺䜣䜙䛛䛾䝠䞁䝖䜢 ᚓ䛶䛔䛯䛰䛡䜜䜀䛸ᛮ䛔䜎䛩䚹

  3. ⮬ᕫ⤂௓ ▼ཎ㷋ኴ㑻 䝕䞊䝍䝃䜲䜶䞁䝔䜱䝇䝖䚸᪥ᮏ⤒῭᪂⪺♫ ኱Ꮫ᫬௦䛿ᕤᏛ㒊䛷᝟ሗᢏ⾡䜢Ꮫ䜃䛴䛴䚸Ꮫ⏕᪂⪺䛷⦅㞟 㛗䛺䛹䜢Ṕ௵䚹ʽ˃ᖺ䛛䜙᪥ᮏ⤒῭᪂⪺♫䛷䚸䝕䞊䝍䝃䜲䜶䞁 䝔䜱䝇䝖䛸䛧䛶グ஦᥎⸀䛺䛹䝕䞊䝍฼ά⏝䛻ྲྀ䜚⤌䜐䚹♫እά ື䛸䛧䛶RÔČČĦø䛻ྲྀ䜚⤌䜏䚸䝁䞁䝨䛾ඃ຾䜔ධ㛛᭩䛄zŸřđIJĬ 䛷䛿䛨䜑䜛RÔČČĦø䝇䝍䞊䝖䝤䝑䜽䛅ฟ∧䜢⤒㦂䚹ʽ˅ᖺᮎ䛻䛿᪥ ᮏ⤒῭᪂⪺♫䛾䝕䞊䝍䝉䝑䝖䜢⏝䛔䛯䝁䞁䝨䜒㛤ദ䛧䛯䚹

  4. 䝔䜽䝜䝻䝆䞊䜢㥑౑䛧䛯䝯䝕䜱䜰௻ᴗ䜈 Ɣ 㟁Ꮚ∧๰หʽʼ࿘ᖺ Ɣ ෆ〇㛤Ⓨ䛷䚸᭱ඛ➃䛾ᢏ⾡䜢ά⏝ Ɣ ʾʼʽ˃ᖺ䛻 øí∧䜢䝸䝙䝳䞊䜰䝹䛧䛂⇿㏿䛃䛜ヰ㢟䛻 ż <IJIJČĦøD͊a䛷z

    ஦౛䛸䛧䛶ゝཬ䛥䜜䜛 Ɣ ⊂⮬䛾䝕䞊䝍ฎ⌮ᇶ┙䛂řĦÔŒ䛃䜢ᵓ⠏䛧a䛷බ㛤 Ɣ Ĕa͊ĬôŎIJĔô䜰䝥䝸㛤Ⓨ䚸䝕䞊䝍䝡䝆䝳䜰䝷䜲䝊䞊䝅䝵䞁䛺䛹䚸᪂䛧䛔᫬௦䛾䝙䝳䞊䝇䛾ᅾ䜚᪉ 䜢 ᶍ⣴䛧䛶䛔䜛 Ɣ ◊✲㛤Ⓨ⤌⧊䛂᪥⤒䜲䝜䝧䞊䝅䝵䞁䞉䝷䝪䛃䜢 ʾʼʽ˃ᖺ䛻タ❧ ż ‡đøIJīŋŞřÔřĔIJĬϊPIJŞŎĬÔĦĔŒīŸīŋIJŒĔŞīʾʼʾʼ䛻䛶䚸◊✲Ⓨ⾲䠄ணᐃ䠅 đNJŋŒ̷͊͊đÔîģ̵ĬĔģģøĔ̵îIJī͊

  5. ᮏ᪥䛾䝔䞊䝬   䝕䞊䝍䝃䜲䜶䞁䝔䜱䝇䝖䛾௙஦䛻䛴䛔䛶 RÔČČĦø䛷຾䛴䛻䛿䠛  䝕䞊䝍ศᯒ⎔ቃ䛸ᩍ⫱