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
Kaggle Google Quest Q&A Labeling - 23th place s...
Search
Shuhei Goda
February 28, 2020
Technology
4
4.1k
Kaggle Google Quest Q&A Labeling - 23th place solution
Shuhei Goda
February 28, 2020
Tweet
Share
More Decks by Shuhei Goda
See All by Shuhei Goda
Turing × atmaCup #18 - 1st Place Solution
hakubishin3
0
890
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
950
とある事業会社にとっての Kaggler の魅力
hakubishin3
8
2.6k
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
1k
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
1.2k
Recommendation Industry Talks #1 Opening
hakubishin3
1
390
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
640
論文紹介: Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment(Xin Xin et al., 2023)
hakubishin3
0
640
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
0
1k
Other Decks in Technology
See All in Technology
生成AIでwebアプリケーションを作ってみた
tajimon
2
150
なぜ私はいま、ここにいるのか? #もがく中堅デザイナー #プロダクトデザイナー
bengo4com
0
450
Кто отправит outbox? Валентин Удальцов, автор канала Пых
lamodatech
0
340
20250625 Snowflake Summit 2025活用事例 レポート / Nowcast Snowflake Summit 2025 Case Study Report
kkuv
1
310
OpenHands🤲にContributeしてみた
kotauchisunsun
1
440
Uniadex__公開版_20250617-AIxIoTビジネス共創ラボ_ツナガルチカラ_.pdf
iotcomjpadmin
0
160
A2Aのクライアントを自作する
rynsuke
1
170
TechLION vol.41~MySQLユーザ会のほうから来ました / techlion41_mysql
sakaik
0
180
How Community Opened Global Doors
hiroramos4
PRO
1
120
低レイヤを知りたいPHPerのためのCコンパイラ作成入門 完全版 / Building a C Compiler for PHPers Who Want to Dive into Low-Level Programming - Expanded
tomzoh
4
3.2k
SalesforceArchitectGroupOsaka#20_CNX'25_Report
atomica7sei
0
170
フィンテック養成勉強会#54
finengine
0
180
Featured
See All Featured
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
7
700
The World Runs on Bad Software
bkeepers
PRO
69
11k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
29
9.5k
RailsConf 2023
tenderlove
30
1.1k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
44
2.4k
Imperfection Machines: The Place of Print at Facebook
scottboms
267
13k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
161
15k
Keith and Marios Guide to Fast Websites
keithpitt
411
22k
GitHub's CSS Performance
jonrohan
1031
460k
Build The Right Thing And Hit Your Dates
maggiecrowley
36
2.8k
Build your cross-platform service in a week with App Engine
jlugia
231
18k
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 !