Ambiguity-aware Ensemble Training for Semi-supervised Dependency Parsing

38 citations recorded by the source corpus.

This paper proposes a simple yet effective framework for semi-supervised dependency parsing at entire tree level,

How researchers see this paper

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

Grammar as a Foreign Language (2014, methodology): “In the second one, we adopt the “tri-training” approach of Li et al. (2014).”
Structured Training for Neural Network Transition-Based Parsing (2015, methodology): “We use same setup as Li et al. (2014), intersecting the output of the BerkeleyParser (Petrov et al.”
Parsing as Language Modeling (2016, methodology): “To obtain silver trees, we parse the entire section of the New York Times (NYT) of the ﬁfth Gigaword (Parker et al., 2011) with a product of eight Berkeley parsers (Petrov, 2010) 2 and ZPar (Zhu et al., 2013) and select 24 million trees on which both parsers agree (Li et al., 2014).”
A Survey of the Usages of Deep Learning for Natural Language Processing (2020, background): “They were able to train on significantly more examples than typical by using tritraining [107], a process in which potential data samples are fed to two other parsers, and those samples upon which both of the parsers agree are used for training the primary parser.”