Into the life of LINE Data Scientist

"初級資料科學家的快樂往往就是這麼樸實無華但不枯燥" by LINE Data Dev - Johnson Wu at LINE Developer Meetup #11 https://linegroup.kktix.cc/events/20200410

Transcript

1. ڡ奍揾ාᑀ䋊ਹጱள䰐ஃஃ ฎ䰼䋿僻嶆֕ӧŏ Johnson Wu, Data Scientist/Machine Learning Engineer LINE Taiwan
2. • 1 3, 3 03 • ,. 023 @ 8C B98 ABC89 BA • ,1 CB 9
3. Data Engineer ML Engineer/Scientist? Data Scientist? Data Analyst
4. ML Engineer/Scientist? Data Scientist?
5. • . / / • / / / . / • / / / A day in the life of a Data Scientist •
6. 2 0 2 0 2 6/ 0 1 / Among the data I processed Figures matter An amount that won’t make you feel as easy as you face at school
7. Skills that fit
8. Projects/activities I participated/ing in LINE • LINE Fact Checker • LINE Music TW • TW User Tagging • SPOT POI recommendation …. • Internal research like automatic speech recognition, reinforcement learning, recommendation task. • Technical sharing like LINE Dev day, LINE Techpulse, R-ladies.
9. - LINE數位當責計畫
10. How ML helps LINE Fact Checker? Verified Messages Similar Messages Total Messages ML Near- Duplication ML Classification
11. ML models • Pre-trained BERT classifier: verify topics • fine-tuned with TODAY articles • A Approximate Nearest Neighbor model: find similar articles
12. ML system under hood Scheduling, Orchestration Serving Training Data Ingestion Async Execution Model Management Model Deployment Index-based Vector Search (ANN)
13. LINE Music TW Toward intelligent music service
    
    
    
14. Simple Data mining: Autocomplete ranking • 18M user query logs using sql to autocomplete
15. Music Knowledge graph on auto-suggest composed compose lyrics_written write_lyircs sing_song same_album
16. Analysis on Music Knowledge graph
17. Research: time for learning • Inside: RL study group, hackathon, and paper reading. • Collaboration with NLP, AD teams in KR, JP side. • External : e.g. Google/AWS/Microsoft workshop, conference.
18. Activities • Let people (not your close colleagues) know what you are doing. • Dev day, TechPulse, R-ladies, AI workshop, internal tech sharing x2.
19. Takeaway • What I‘ve been doing: finding data-driven solutions for project needs • Knowledge graph, Speech recognition, POI recommendation, Embedding, ML. • Data x ML x optimization x speech • Plain but fun J
20. About our Team : Data dev team TW
21. We are hiring!