Meta
  • Our approach
  • Research
  • Product experiences
  • Llama
  • Blog
  • Try Meta AI

    • Elena Voita

    RESEARCH SCIENTIST | LONDON, UNITED KINGDOM

    Elena (Lena) Voita is a Research Scientist at FAIR working on Analysis and Interpetability for NLP. She is also NLP Course For You creator and SIGREP president (2022-2024). Lena received her Ph.D. at the University of Edinburgh and was supervised by Ivan Titov and Rico Sennrich. During her study, she was awarded Facebook PhD Fellowship.

    Google Scholar

    GitHub

    Personal Website

    Twitter

    Research Areas

    Natural Language Processing (NLP)

    Elena's Work

    NLP Course For You

    Natural Language Processing course with interactive lectures-blogs, research thinking exercises and related papers with su...

    BPE-Dropout: Simple and Effective Subword Regularization

    Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

    Information-Theoretic Probing with MDL

    Bottom-Up Evolution of Representation in the Transformer

    LLM Transparency Tool

    Interactive Tool for Analyzing Transformer Language Models (ACL Demo)

    Elena's Publications

    August 11, 2024

    NLP

    LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models

    Igor Tufanov, Karen Hambardzumyan, Javier Ferrando, Lena Voita

    August 11, 2024

    Read the Paper

    June 25, 2024

    NLP

    Neurons in Large Language Models: Dead, N-gram, Positional

    Elena Voita, Javier Ferrando Monsonis, Christoforos Nalmpantis

    June 25, 2024

    Read the Paper

    June 13, 2024

    NLP

    Know When To Stop: A Study of Semantic Drift in Text Generation

    Ava Spataru, Eric Hambro, Lena Voita, Nicola Cancedda

    June 13, 2024

    Read the Paper
    Our approach
    About AI at Meta
    Responsibility
    People
    Careers
    Research
    Infrastructure
    Resources
    Demos

    Product experiences

    Meta AI
    AI Studio
    Latest news
    Blog
    Newsletter

    Foundational models

    Llama
    Privacy Policy
    Terms
    Cookies

    Meta © 2024