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

Utilizing Embeddings 
 In Learning To Rank 
 For Search

Utilizing Embeddings 
 In Learning To Rank 
 For Search

BY Shawn Tsai @LINE TECHPULSE 2019 https://techpulse.line.me/

2102a6b8760bd6f57f672805723dd83a?s=128

LINE Developers Taiwan
PRO

December 04, 2019
Tweet

More Decks by LINE Developers Taiwan

Other Decks in Programming

Transcript

  1. None
  2. Utilizing Embeddings 
 In Learning To Rank 
 For Search

    > Shawn TSAI / LINE Taiwan Data Dev
  3. Agenda > Search Everywhere > Search Result Relevance > Embeddings

    > Learning To Rank > Search Workflow
  4. Search Everywhere Life on LINE

  5. Search Result Relevance > The main goal is to reduce

    the semantic gap between user query and documents. > The key points: semantic features and ranking function. > Search is a ranking problem. The ordering is more important than the predicted probability of a single instance.
  6. > 聊天記錄⼀一直在資料壓縮中 > 不管怎麼按備份聊天紀錄都不能備份 Limitation: Different description Limitation: No shared

    keywords > 為什什麼有時候賴都不會通知 > 訊息都跑不出來來是怎樣 Search Scoring & Limitation > , > ( ) = () = 1 + + 1 + 1 _ = ∗ Standard similarity function: TF-IDF
  7. Embeddings

  8. Word Embedding > Vector representation > Capturing context of a

    word in a document, semantic/syntactic similarity, relation with other words Source: Efficient Estimation of Word Representations in Vector Space
  9. BERT BERT is a new method of pre-training language representations

    which obtains state-of-the-art results on a wide array of NLP tasks. Source: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Bidirectional Encoder Representations from Transformers
  10. Querying By Vector Representation Sent. Encoding
 By Pre-trained BERT
 Model

    Query Document Vecs Index Query Vec Documents Document Vecs Online Offline Nearest Neighbor Search Build 
 NN 
 Index
  11. Learning To Rank

  12. Learning To Rank > Applying machine learning to construct ranking

    models for information retrieval systems > Caring more about ranking rather than rating prediction > Scoring by machine learning • Creating document index by Elasticsearch • Using embeddings to train ranking models • Serving search queries by Elasticsearch with ranking models
  13. Filters Search Architecture Documents Query Filter Index ES + Re-ranking

    BERT Matches Ranked Results NER … Scoring Index Ranking Models
  14. Ƃ Custom Scoring Function Ƃ

  15. Search Workflow With Learning To Rank User’s Needs Measure Relevance

    Pre-process Inverted-index Features Selection Ranking Models Scoring Function NDCG MAP Precision@k Deploy Monitoring Feedback Evaluation Build Index Learning To Rank Serve Data
  16. More Consideration > Good judge lists matching user needs of

    search quality > Good metrics measuring search results > Incorporating with embeddings into scoring function > Synchronizing the version between indexing and serving layers > A/B testing
  17. Thank you