Share
Embed
Toward Intelligent Music Service
Johnson Wu
LINE Taiwan Data Team Data Scientist
LINE DevDay 2019
November 20, 2019
Transcript
16 slides
-
2019 DevDay Toward Intelligent Music Service > Johnson Wu >
LINE Taiwan Data Team Data Scientist -
Self-Introduction • Johnson Wu • 2019.03 Join as Data Scientist
@ LINE TW data dev team • Providing data-driven solutions for local projects • LINE Fact-Checker, LINE MUSIC TW, User Tagging, General dictionary services …etc. -
Agenda > AI technology on LINE MUSIC TW > Module
introduction > Future works -
AI Technology on LINE MUSIC TW How AI can be
applied ? A basic start. > Name Entity Recognition > Link prediction > Word Embedding Knowledge Graph With User Query Extraction of Knowledge From Unstructured Data > Link prediction Auto-Complete Recommendation > SmartText AutoComplete > A trie-based structure model for popularity and correction on Chinese words. -
AutoComplete Start from a simple service, in a search bar!
Auto-complete user query with popularity search query - the source to start knowledge extraction From 20M+ user queries, 4M+ music dataset E G L E S R T H A … Eagles ? Earth song ? Ea… -
Module Introduction How to do auto-complete with popularity? Trie-based search
solution trained on 20M+ user query logs. auto-complete ranking #(Eagles) > #(ear) > #(earth) E G L E S R T H A … Search Count: 100 Search Count: 50 Search Count: 60 homophones are trained for spell correction as well ӽఴʢwu yue tien)→ޒ݄ఱ AutoComplete on Recent popular queries First word Complete 31.84% acc Saving input % 34% Middle word Complete 89.93% acc -
AI Technology on LINE MUSIC TW How AI can be
applied ? Could we understand user’s query? > Name Entity Recognition > Link prediction > Word Embedding Knowledge Graph With User Query Extraction of Knowledge From Unstructured Data > Link prediction Auto-Complete Recommendation > SmartText AutoComplete > A trie-based structure model for popularity and correction on Chinese words. -
Prediction of relationship, entities on the user queries or extracted
triples. ᤚґྛ Womxnly ᤚґྛ Ugly Beauty ᤚґྛ Lady in Red ᤚґྛ Life Sucks Muse ෆམ Ѩ৴ ۚଟ՜ ంḚ ࡾߋ … Link Prediction (1/2) Auto-suggesting with knowledgeable results sing_song Jolin Tsai sing_song Ugly Beauty Lady in Red Life Sucks Wom xnly lyrics_written Ѩ ৴ eng_name ం Ḛ composed ࡾߋ compose ۚ ଟ՜ write_lyrics ᙽ ڰੈք ީௗ ਓ ੜ༗ݶ ެ࢘ same_album Mus e ෆམ eng_name -
Prediction of relationship, entities on the user queries or extracted
triples. Link Prediction (2/2) Auto-suggesting with knowledgeable results Related Singers ? Jolin Tsai sing_song Ugly Beauty զ ዑ∍ ײ ᧷㟬త ଘࡏ Jay Chou eng_name eng_name Knight sprint Pirat e Say love you sing_song: Songs ranked by popularity compose 㘸 ෆᄠ ࠂ നᔅٿ ෆ ֘ Knight Spirit Pirate Say Love You Popcorn’s Flavor This Is Love 㘸ෆᄠ (by Jay Chou) ࠂനᔅٿ (by Jay Chouʣ ෆ֘ʢby Jay Chouʣ … -
Module Introduction How to do knowledge extraction? GraphSpace: a StarSpace-based
solution of word embedding model on entity/relation prediction from a query/triple input. Trained on 4M entities and 36M relation triples. Example of word analogy: female_singer chinese_named_song #relation: sing_song ᤚґྛ ት #sing_song ߐ↠ Ոޙ #sing_song ҆ࣨಸඒዳ 䆪ᄒ࣌ঘঁԦ #sing_song -
AI Technology on LINE MUSIC TW How AI can be
applied ? > Name Entity Recognition > Link prediction > Word Embedding Knowledge Graph With User Query Extraction of Knowledge From Unstructured Data > Link prediction Auto-Complete Recommendation > SmartText AutoComplete > A trie-based structure model for popularity and correction on Chinese words. -
Extract name entities from unstructured articles; compliment related search. Name
Entity Recognition Explore knowledge from our data! YOU & I Coco Lee Randy Merrill Lady Gaga 㐋 䆾 ፮֨ݭ ᒜᅶ Singer of the Song Detected Entities Related to This Song GJ ḚՅ Ұ ݸڊత ੜ Album Intro -
Module Introduction(3/3) How to do name entity recognition? A fine-tuned
BERT with bi-lstm based decoder model. Costum tags like “Singer”, “Song ”, “Album”, “Composer”, “Lyric writer”, “Album producer” Model NER F1-score on costum tags Bert+Bilstm 0.63 Bilstm 0.21 Original text NER results 48,190 album articles 54,762 NER valid detections -
Summary Takeaway 1. A convenient autocomplete function for search service
2. Knowledge graph solution for more intelligent auto-suggest 3. A potential way to extract knowledge from unstructured data. -
Future Works Making the model better 1. Higher accuracy on
NER recognition. 2. More contents to recognize from unstructured articles. A. Singer style B. Song music Style 3. Human Evaluation designs. 4. Better efficiency for application service.