Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Kaggle Google Quest Q&A Labeling - 23th place s...
Search
Shuhei Goda
February 28, 2020
Technology
4.3k
4
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Kaggle Google Quest Q&A Labeling - 23th place solution
Shuhei Goda
February 28, 2020
More Decks by Shuhei Goda
See All by Shuhei Goda
Turing × atmaCup #18 - 1st Place Solution
hakubishin3
0
1.3k
ジョブマッチングサービスにおける相互推薦システムの応用事例と課題
hakubishin3
3
1.2k
とある事業会社にとっての Kaggler の魅力
hakubishin3
9
3.3k
課題の解像度が荒かったことで意図した改善ができなかった話
hakubishin3
3
1.2k
Wantedly におけるマッチング体験を最大化させるための推薦システム
hakubishin3
4
1.4k
Recommendation Industry Talks #1 Opening
hakubishin3
1
490
会社訪問アプリ「Wantedly Visit」での シゴトに関する興味選択機能と推薦改善
hakubishin3
0
810
論文紹介: Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment(Xin Xin et al., 2023)
hakubishin3
0
750
Feedback Prize - English Language Learning における擬似ラベルの品質向上の取り組み
hakubishin3
1
1.2k
Other Decks in Technology
See All in Technology
DevelopersIO2026 -バックアップは“消されないこと”が9割-
yoshida0129
0
340
野蛮なアジャイル [サイボウズ発!]組織の常識を覆した反骨のスクラム実践記 / Barbaric Agile - Enterprise Agile Study Group
ama_ch
0
130
React改造してみた
tsukina_7mochi
0
150
顧客価値を追いかけたら、プライシングにたどり着いた
sansantech
PRO
2
580
Classmethod Company Deck
satoshi7
1
820
Railsで挑む大量データ永続化 〜600億件を永続化するための設計とボトルネックとの戦い〜
occhi
1
1.1k
Claude Code on Bedrock で統制をかける小ネタ集/claude-code-bedrock-governance-tips
emiki
1
420
生成AI時代、PMは事業責任者に進化するともっと面白い〜PMだからこそ事業構造を動かせる時代に〜
kakehashi
PRO
0
450
CloudWatch Logsのコスト最適化:どこまでAIに任せてどこから人間が承認すべきか
yama3133
0
170
Teaching Python with three kinds of AI
reuven
0
100
Tofu-Controller lightning talk @ Containerday 2026
gionn
0
190
JAWS-UGグッズ職人仕事の流儀
kentapapa
0
140
Featured
See All Featured
Effective software design: The role of men in debugging patriarchy in IT @ Voxxed Days AMS
baasie
1
580
Why You Should Never Use an ORM
jnunemaker
PRO
61
10k
ラッコキーワード サービス紹介資料
rakko
3
5.4M
Kristin Tynski - Automating Marketing Tasks With AI
techseoconnect
PRO
0
550
4 Signs Your Business is Dying
shpigford
187
23k
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
Paper Plane (Part 1)
katiecoart
PRO
2
12k
Public Speaking Without Barfing On Your Shoes - THAT 2023
reverentgeek
1
610
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
2.2k
30 Presentation Tips
portentint
PRO
1
430
Rebuilding a faster, lazier Slack
samanthasiow
85
9.7k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.9k
Transcript
©2020 Wantedly, Inc. 23th place solution Kaggle Google Quest Q&A
Labeling লձ Feb 28, 2020 - Shuhei Goda - @jy_msc
©2020 Wantedly, Inc. Team - The Hand Shuhei Goda @jy_msc
Visit Engineering Team at Wantedly Naomichi Agata @agatan_ People Engineering Team at Wantedly
©2020 Wantedly, Inc. Model Pipeline #FSUCBTF VODBTFE -JHIU(#. #FSUCBTF VODBTFE
Settings ɾ3fold with GroupKFold ɾBCE + margin ranking loss ɾ3epoch Settings ɾmax_depth=1 ɾlr=0.1 Meta features ɾtext length ɾstackexchange Text data ɾquestion_title ɾquestion_body ɾanswer 1SF1SPDFTT 2BOE" 1SF1SPDFTT POMZ2 ɾquestion_title ɾquestion_body ɾquestion_title ɾquestion_body ɾanswer Settings ɾhtml escape ɾhead+tail truncation
©2020 Wantedly, Inc. ɾHTMLจࣈྻͷΞϯΤεέʔϓ Pre-Process IUUQTXXXLBHHMFDPNDHPPHMFRVFTUDIBMMFOHFEJTDVTTJPO
©2020 Wantedly, Inc. ɾςΩετσʔλͷ݁߹ͱτϦϛϯά ɹɾ[CLS] + question_title + [SEP] +
question_body + [SEP] + answer ɾquestion_body ͱ answer ͕ࢦఆͷ͞Λ͑ͨ߹, ͔྆ΒಉαΠζΛτϦϛϯά Pre-Process IUUQTBSYJWPSHBCT
©2020 Wantedly, Inc. ɾBert-base (uncased) ɹɾޙΖ4ͭͷӅΕͷग़ྗΛ༻ https://arxiv.org/abs/1905.05583 ɹɾQAؒͷSEP tokenͷग़ྗΛ༻ Model
Architecture
©2020 Wantedly, Inc. ɾLabel weight ɹɾ؆୯ͦ͏ͳλεΫweightΛখ͘͞, ෆۉߧͰͦ͠͏ͳλεΫweightΛେ͖͘ ɹɾgpyoptͰweightͷ୳ࡧΛࢼͨ͠Έ͕ͨ, Լهͷ୯७ͳΓํ͕࠷ྑ͔ͬͨ Loss
function Label weight ͋Γ Public: 0.45979, Private: 0.41440 Label weight ͳ͠ Public: 0.43455, Private: 0.40602
©2020 Wantedly, Inc. ɾBCE + margin ranking loss (1 :
1) ɹɾϛχόονΛ2ͭʹׂͯ͠ margin ranking loss Λܭࢉ Loss function BCE + margin ranking loss Public: 0.45979, Private: 0.41440 BCE Public: 0.44006, Private: 0.40668
©2020 Wantedly, Inc. ɾQuestion Model ɹɾQ༻ͷλεΫΛQuestion text͚ͩΛͬͯղ͘ ɹɾΠϯϓοτQ͚ͩͰ͍͍ͷͰ, Qͷtruncationͷྔ͕ݮΔ (Qͷใྔ͕૿͑Δ)
Training Q model + Q and A model Public: 0.45979, Private: 0.41440 Q and A model × 2 (seed average) Public: 0.44298, Private: 0.40613
©2020 Wantedly, Inc. ɾLightGBM ɹɾmax_depth=1, lr=0.1 ɹɾmeta features ɹɹɾtext length
(question, answer) ɹɹɾmeta data from stackexchange (Score, View, FavoriteCount, …) Post-Process LightGBM Public: 0.45979, Private: 0.41440 Simple binning without meta features Public: 0.45282, Private: 0.41387
©2020 Wantedly, Inc. Why we used LightGBM? 1. Simple binning
method ɹɾ༧ଌΛࢄԽ͢Δ͜ͱͰ Spearman’s correlation ͕ྑ͘ͳΔ͜ͱʹؾͮ͘ ɹɾtarget͝ͱʹϏϯαΠζΛࣄલʹઃఆͯ͠Ϗϯೋϯά ɹɾϏϯαΠζݻఆʹ্ͨ͠ͰBertͷ֤epochͷग़ྗΛweighted average (weight࠷దԽ)
©2020 Wantedly, Inc. Why we used LightGBM? 2. Optimize bin-size
and weights ɹɾϏϯαΠζ࠷దͳΛ͍ͨ͘ͳͬͨ ɹɾϏϯαΠζͱweightsͷಉ࣌࠷దԽ্͕ͨ͠ख͍͔͘ͳ͍ ɹɾ࠷దͳϏϯαΠζ༧ଌͷܗʹΑܾͬͯ·Δ. ֤foldͷ࠷దͳϏϯαΠζͷฏۉͱ weighted averageޙͷ༧ଌ࠷దͳͷ͔Βဃ͢Δ
©2020 Wantedly, Inc. Why we used LightGBM? 3. LightGBM ɹɾϏϯαΠζͱweightsͷಉ࣌࠷దԽ͍ͨ͠
ɹɾmeta features͍͍ͨ ɹɾGBDTσʔλΛׂׂͯ͠ޙͷྖҬʹ࠷దͳΛׂΓͯΔख๏ ɹɹˠ ઙ͍߹Ϗϯχϯάͱಉ༷ͷࢄԽ͕Ͱ͖ΔΜ͡Όͳ͍͔ max_depth=2 max_depth=8
©2020 Wantedly, Inc. 4. LightGBM (parameter tuning) ɹɾࢄԽ͢Δ΄Ͳscore͕ྑ͘ͳΔͷͰ, ߏΛۃྗγϯϓϧʹ͍ͨ͠ ɹɾtrainσʔλΛׂͯ͠࠷దͳύϥϝʔλΛݟ͚ͭΔ
ɹɾmax_depthΛҰ൪খ͘͞, lrΛۃྗେ͖ͨ͘͠ํ͕score͕ྑ͘ͳͬͨ Why we used LightGBM?
©2020 Wantedly, Inc. ɾsample weightͷઃఆ ɾhostͷ୯ޠΛΠϯϓοτͷઌ಄ྻʹஔ͘ ɾnew tokenͷՃ ɾBert-base casedΛ͏
ɾtexͷίʔυϒϩοΫΛྗٕͰফڈ Didn’t work for us
©2020 Wantedly, Inc. Discussion: https://www.kaggle.com/c/google-quest-challenge/discussion/129904#742302 Kernel: https://www.kaggle.com/shuheigoda/23th-place-solusion Links
©2020 Wantedly, Inc. https://www.wantedly.com/projects/375150 We are hiring !