NLP Wiki

User Tools

Site Tools

Trace: • post-training • embodied_ai • ethics • privacy • large_reasoning_models • catastrophic_forgetting • ensembling • confidence • graph_nn
ml:distribution_shift

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
ml:distribution_shift [2022/09/21 00:56] – [People] jmflanigml:distribution_shift [2023/07/26 18:59] (current) – jmflanig
Line 12: Line 12:
   * [[https://arxiv.org/pdf/2109.01558.pdf|Michel 2021 - Learning Neural Models for Natural Language Processing in the Face of Distributional Shift]] PhD thesis   * [[https://arxiv.org/pdf/2109.01558.pdf|Michel 2021 - Learning Neural Models for Natural Language Processing in the Face of Distributional Shift]] PhD thesis
   * [[https://arxiv.org/pdf/2204.06340.pdf|Michel 2022 - Distributionally Robust Models with Parametric Likelihood Ratios]]   * [[https://arxiv.org/pdf/2204.06340.pdf|Michel 2022 - Distributionally Robust Models with Parametric Likelihood Ratios]]
 +
 +===== Distribution Shift / Out-of-Domain Detection =====
 +  * **In NLP**
 +    * [[https://aclanthology.org/2023.acl-long.717.pdf|Uppaal et al 2023 - Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection]]
  
 ===== Datasets ===== ===== Datasets =====
ml/distribution_shift.1663721817.txt.gz · Last modified: 2023/06/15 07:36 (external edit)
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki