Artificial Intelligence and Collective Intelligence

By Daniel S. Weld, C. H. Lin, Jonathan Bragg. 2014

34 citations recorded by the source corpus.

Subfields: Social Sciences & Humanities

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Social Sciences & Humanities

1. Noah A. Smith
2. Michael S. Bernstein
3. Daniela Retelny
4. Li Fei-Fei
5. Melissa A. Valentine

Citations in the corpus

• All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text (2021, methodology): “Based on our findings, if NLG researchers must run human evaluations as small-batch evaluations on Amazon Mechanical Turk or similar platforms, we recommend they train evaluators with examples.”
• HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models (2019, background): “In the case of text generation (translation, caption generation), HYPEtime will require much longer and much higher range adjustments to the perceptual time thresholds [29, 59].”
• No Workflow Can Ever Be Enough (2017, methodology): “Many of these systems rely on crowdsourcing workflows, which are a set of pre-defined tasks that have been decomposed and are computationally sequenced and assigned to distributed workers to complete [43, 44, 67].”