PCA News

PCA news retweets the most interesting machine learning conversations on Twitter.
Subscribe to the weekly newsletter:

[PCA News @PcaNews]

Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages
https://t.co/qHpFUF6Kqn
https://t.co/OAuqNjXby3

[Edoardo Ponti @PontiEdoardo]

Given the paucity of annotated data, how can we perform sample-efficient generalization on unseen task-language combinations? Possible solution: a generative model of the neural parameter space, factorized into variables for several languages and tasks. 1/2

[PCA News @PcaNews]

PCA(news) papers for January 27 - February 2:

[PCA News @PcaNews]

PMIndia -- A Collection of Parallel Corpora of Languages of India
https://t.co/vUlMDLd26e
https://t.co/DRFptn8W2k

[Barry Haddow @bazril]

Pleased to announce the release of PMIndia, a parallel corpus featuring 13 languages of India paired with English. Corpus: https://t.co/D72Z0CWlTB Paper: https://t.co/ip9XJZaa6Y .Part of the @GoURMET_MT project.

[PCA News @PcaNews]

A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
https://t.co/ocHO0zGh6q
https://t.co/yeNmBK6qy0

[PCA News @PcaNews]

PCA(news) papers for January 20 - January 26:

[PCA News @PcaNews]

GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
https://t.co/qpRbL3TDKX
https://t.co/BDO2p1dSOy