Graham Neubig, Bhuwan Dhingra, Zachary Lipton, Danish Pruthi
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
For many prediction tasks, stakeholders desire not only predictions but also supporting evidence that a human can use to verify its correctness. However, in practice, evidence annotations may only be available for a minority of training examples (if available at all). In this paper, we propose new methods to combine few evidence annotations (strong semisupervision) with abundant document-level labels (weak supervision) for the task of evidence extraction. Evaluating on two classification tasks that feature evidence annotations, we find that our methods outperform baselines adapted from the interpretability literature to our task. Our approach yields gains with as few as hundred evidence annotations. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2011.01459")
get_code_for_paper("2011.01459")
have("2011.01459")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2011.01459.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2011.01459)
Connect an agent — have() is free.