8 papers
Joint and conditional estimation of tagging and parsing models
Mark Johnson
This paper compares two different ways of estimating statistical language models. Many statistical NLP tagging and parsing models are estimated by maximizing the (joint) likelihood…
Compact non-left-recursive grammars using the selective left-corner transform and factoring
Mark Johnson, Brian Roark
The left-corner transform removes left-recursion from (probabilistic) context-free grammars and unification grammars, permitting simple top-down parsing techniques to be used. Unfo…
Explaining away ambiguity: Learning verb selectional preference with Bayesian networks
Massimiliano Ciaramita, Mark Johnson
This paper presents a Bayesian model for unsupervised learning of verb selectional preferences. For each verb the model creates a Bayesian network whose architecture is determined…
Efficient probabilistic top-down and left-corner parsing
Brian Roark, Mark Johnson
This paper examines efficient predictive broad-coverage parsing without dynamic programming. In contrast to bottom-up methods, depth-first top-down parsing produces partial parses…
Type-driven semantic interpretation and feature dependencies in R-LFG
Mark Johnson
Once one has enriched LFG's formal machinery with the linear logic mechanisms needed for semantic interpretation as proposed by Dalrymple et. al., it is natural to ask whether thes…
The effect of alternative tree representations on tree bank grammars
Mark Johnson
The performance of PCFGs estimated from tree banks is sensitive to the particular way in which linguistic constructions are represented as trees in the tree bank. This paper presen…