Differences

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

--- ml:multi-task_learning [2022/07/20 08:44] – created jmflanig
+++ ml:multi-task_learning [2023/06/15 07:36] (current) – external edit 127.0.0.1
@@ Line 4: / Line 4: @@
 ===== In NLP =====
-  * [[Kaiser et al 2017 - One Model To Learn Them All]] Almost the same authors as the Transformer (submitted four days after the Transformer).  Interesting they didn't use the Transformer.  Perhaps they got the inspiration from this work.
+  * [[https://arxiv.org/pdf/1706.05137.pdf|Kaiser et al 2017 - One Model To Learn Them All]] Almost the same authors as the Transformer (submitted four days after the Transformer).  Interesting they didn't use the Transformer.  Perhaps they got the inspiration from this work.
+  * DecaNLP: [[https://arxiv.org/pdf/1806.08730.pdf|McCann et al 2018 - The Natural Language Decathlon: Multitask Learning as Question Answering]] [[https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1194/slides/cs224n-2019-lecture17-multitask.pdf|slides]] [[https://decanlp.com/|dataset]]
-==== Related Pages =====
+===== Datasets =====
-  *
+  * NLP
+    * [[https://decanlp.com/|DecaNLP]] [[https://arxiv.org/pdf/1806.08730.pdf|paper]]
+===== Related Pages =====
+  * [[Meta-Learning]]