ICLR
|
2022
J. Zhang, et al
Abstract
This paper extends the scope of usable sources in WS, by formulating Weak Indirect Supervision (WIS), a new research problem for automatically synthesizing training labels based on indirect supervision sources that have different output label spaces.
Coming Fall 2026
A one-day, invite-only summit providing a first look at the benchmarks and research that will shape the frontier. Sign up for updates.