We attempt to address that challenge by proposing a novel approach to the problem: Local Intrinsic Dimension estimation using approximate Likelihood (LIDL).
The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks.
A reduction of quadratic time and memory complexity to sublinear was achieved due to a robust trainable top-$k$ operator.
Ranked #2 on Text Summarization on arXiv Summarization Dataset
We introduce a simple new approach to the problem of understanding documents where non-trivial layout influences the local semantics.
Ranked #3 on Key Information Extraction on Kleister NDA