Semanlink - shikhar sur Twitter : "Instead of asking whether tree structure should be baked into NNs, our new paper asks if transformers already have a tendency to learn tree structured computations when trained on language, and if this structure is predictive of generalization! "

Printer friendly

Search Tag:

Search Doc:

Preferences...

shikhar sur Twitter : "Instead of asking whether tree structure should be baked into NNs, our new paper asks if transformers already have a tendency to learn tree structured computations when trained on language, and if this structure is predictive of generalization! "

Tags:

About This Document

sl:bookmarkOf : https://twitter.com/ShikharMurty/status/1600931878789599235
sl:creationDate : 2022-12-09
sl:creationTime : 2022-12-09T11:30:35Z

File info

Bookmark of: https://twitter.com/ShikharMurty/status/1600931878789599235

Documents with similar tags (experimental)

Seth Stafford sur Twitter : "Here’s a nice paper (ICLR spotlight) on how to apply masking in LM training..."

Tags:

2021-10-16 About