Association for Computing Machinery

By Eric Horvitz. 2009

How researchers see this paper

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

In Evaluation & Benchmarks

Citations in the corpus

Understanding Dataset Difficulty with V-Usable Information (2021, neutral): “Text-based heuristics such as word identity (Bengio et al., 2009) or input length (Spitkovsky et al., 2010; Gururangan et al., 2018) have sometimes been used as proxies for instance difficulty, but offer limited insight into difficulty w.r.t. models.”
Data-Efficient Structured Pruning via Submodular Optimization (2022, methodology): “In another class of methods called knowledge distillation, a small network is trained to mimic a much larger network [Bucila et al., 2006, Hinton et al., 2015].”
Truth Is a Lie: Crowd Truth and the Seven Myths of Human Annotation (2015, background): “2013; Kittur, Chi, and Suh 2008; Ipeirotis, Provost, and Wang 2010), and analyze workers perfomance for quality control and optimization of the crowdsourcing processes (Singer and Mittal 2013).”
Self-Distillation Amplifies Regularization in Hilbert Space (2020, methodology): “Knowledge distillation was introduced in the deep learning setting [13] as a method for transferring knowledge from one architecture (teacher) to another (student), with the student model often being smaller (see also [5] for earlier ideas).”
DARPA's Explainable Artificial Intelligence (XAI) Program (2019, background): “The explainer outputs an explanatory parse graph in a dialogue process (She and Chai 2017), localizes the relevant subgraph in the STC-PG, and infers the user’s intent.”
Googling Investor Sentiment around the World (2019, unknown): “We start with a description of construction procedures and then highlight the differences between our method and the Da et al. (2015) approach.”