Self-Training with Products of Latent Variable Grammars

We study self-training with products of latent variable grammars in this paper. We show that increasing the quality of the automatically parsed data used for self-training gives higher accuracy self-trained grammars. Our generative self-trained grammars reach F scores of

• Type: Journal
• Year: 2010
• Where: EMNLP
• Authors: Zhongqiang Huang, Mary P. Harper, Slav Petrov
• Keywords: Accuracy Self-trained Grammars, EMNLP 2010, Latent Variable Grammars, Natural Language Processing, Self-trained Grammars