Massive Text Embedding Benchmark: A global effort to expand text embedding evaluation to all languages

  • Enevoldsen, Kenneth Christian (PI)
  • Bernstorff, Martin (Participant)
  • Kardos, Márton (Participant)
  • Kerboua, Imene (Project coordinator)
  • Schaeffer, Marion (Participant)
  • Xiao, Shitao (Participant)
  • Cassano, Federico (Participant)
  • Li, Wen-Ding (Participant)
  • Rystrøm, Jonathan (Participant)
  • Lee, Taemin (Participant)
  • Zhang, Xin (Participant)
  • Weller, Orion (Participant)

Project: Research

Project Details

Description

Massive Text Embedding Benchmark (MMTEB) is a global effort to expand text embedding evaluation to all languages with more than 50 contributors. The benchmark seeks to evaluate the quality of embeddings of text, e.g. used for search, retrieval etc.
Short titleMassive Text Embedding Benchmark
AcronymMMTEB
StatusActive
Effective start/end date01/04/2024 → …

Keywords

  • Natural Language Processing
  • Information Retrieval
  • Evaluation
  • Artificial intelligence