Aaron Smith

Natural Language Processing · with Li · 2014–2017

A researcher in the Science corpus: 2 papers; trusts 6 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

Whom Aaron Smith trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

  1. Franz Joseph Och
  2. Andreas Stolcke
  3. Kenneth Heafield
  4. Jörg Tiedemann

Papers from Aaron Smith's perspective

Ordered by how strongly the researchers Aaron Smith trusts endorse each paper. Same corpus, a different order for every researcher.

  1. An Empirical Study of Smoothing Techniques for Language Modeling
  2. Minimum Error Rate Training in Statistical Machine Translation
  3. SRILM - an extensible language modeling toolkit
  4. Class-Based n-gram Models of Natural Language
  5. KenLM: Faster and Smaller Language Model Queries
  6. A Simple, Fast, and Effective Reparameterization of IBM Model 2
  7. Clause Restructuring for Statistical Machine Translation
  8. Parallel Data, Tools and Interfaces in OPUS
  9. The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compression
  10. Improving a Statistical MT System with Automatically Learned Rewrite Patterns (International Conference on Computational Linguistics)

Their papers