Semi-Supervised Structured Output Learning Based on a Hybrid Generative and Discriminative Approach

By Jun Suzuki, Akinori Fujino, Hideki Isozaki. 2007

40 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Probabilistic & Bayesian Methods

How researchers see this paper

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

In Representation & Self-Supervised Learning

1. Andrew McCallum
2. Gideon S. Mann
3. Percy Liang
4. Jun Suzuki
5. Hideki Isozaki
6. Stefan Wager
7. Sida I. Wang
8. Burr Settles

In Probabilistic & Bayesian Methods

1. Andrew McCallum
2. Gideon S. Mann
3. Jun Suzuki
4. Hideki Isozaki
5. Percy Liang
6. Stefan Wager
7. Sida I. Wang
8. Yura N. Perov

Citations in the corpus

• Dropout Training as Adaptive Regularization (2013, background): “Most approaches to semi-supervised learning either rely on using a generative model [19, 20, 21, 22, 23] or various assumptions on the relationship between the predictor and the marginal distribution over inputs.”
• Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data (2010, methodology): “In a classic result (Merialdo, 1994) attempts semi-supervised learning to improve HMM part-of-speech tagging and finds that EM with unlabeled data reduces accuracy.”
• Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data (2008, methodology): “Following this idea, there have been introduced a parameter estimation approach for non-generative approaches that can effectively incorporate unlabeled data (Suzuki et al., 2007).”