Probabilistic Models of Nonprojective Dependency Trees

A notable gap in research on statistical dependency parsing is a proper conditional probability distribution over nonprojective dependency trees for a given sentence. We exploit the Matrix Tree Theorem (Tutte, 1984) to derive an algorithm that efficiently sums the scores of all nonprojective trees in a sentence, permitting the definition of a conditional log-linear model over trees. While discriminative methods, such as those presented in McDonald et al. (2005b), obtain very high accuracy on standard dependency parsing tasks and can be trained and applied without marginalization, “summing trees” permits some alternative techniques of interest. Using the summing algorithm, we present competitive experimental results on four nonprojective languages, for maximum conditional likelihood estimation, minimum Bayes-risk parsing, and hidden variable training.

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: David A. Smith, Noah A. Smith
• Keywords: Dependency Parsing, EMNLP 2007, Natural Language Processing, Nonprojective Dependency Trees, Statistical Dependency Parsing