Titlebook: Semi-Supervised Dependency Parsing; Wenliang Chen,Min Zhang Book 2015 Springer Science+Business Media Singapore 2015 Big Data for Parsing.

expository

Book 2015recent works which utilize different types of information gleaned from unlabeled data. The book offers readers a comprehensive introduction to these approaches, making it ideally suited as a textbook for advanced undergraduate and graduate students and researchers in the fields of syntactic parsing and natural language processing.

JUST

covert

Training with Bilexical Dependencies,ng accuracy. First, all the sentences in the unlabeled data are parsed by a baseline parser. Subsequently, information on short dependency relations is extracted from the parsed data, because the accuracies for short dependencies are relatively higher than those for others. Finally, we train another

使人烦燥

Training with Meta-features, bi- and tri-gram lexical subtree structures. It can be extended further. The base features defined over surface words, part-of-speech tags represent more complex tree structures than bilexical dependencies and lexical subtrees.

向外供接触

希望

biopsy

Dependency Parsing Models,In this chapter, we describe the data-driven supervised dependency parsing models and then summarize the recent reported performance of previous work on Penn English Treebank, a widely used data set.

Lipoprotein

Alveoli

Monotonous

Training with Subtree Structures,In this chapter, we introduce a semi-supervised approach of using subtree structures to improve dependency parsing. The subtrees are extracted from dependency trees in auto-parsed data, and a set of subtree-based features is designed for the parsing models.