Mandatory Reading Material

  1. WordPiece and BPE tokenizer papers
  2. SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
  3. A study of smoothing methods for language models applied to information retrieval
  4. C.J.C. Burges, From RankNet to LambdaRank to LambdaMART: An Overview. Microsoft Research Technical Report MSR-TR-2010-82, 2010
  5. C.J.C. Burges, R. Ragno and Q.V. Le, Learning to Rank with Non-Smooth Cost Functions. NIPS 2006
  1. Survey on Open-Vocabulary Modeling and Tokenization in NLP (Mielke et al.)
  2. The Probabilistic Relevance Framework: BM25 and Beyond
  3. A study of Poisson query generation model for information retrieval
  4. Efficient Estimation of Word Representations in Vector Space (Aka the Word2Vec paper)
  5. Neural Word Embedding as Implicit Matrix Factorization
  6. Dependency-Based Word Embeddings
  7. A Dual Embedding Space Model for Document Ranking (Extended version of the WWW’16 paper)