We would like to acknowledge the annotators who participated in the tagging of this corpus and previous work leading up to this effort. Their contributions to the ideas presented here are significant: This reference manual presents the guidelines used to develop a large discourse-annotated corpus for community-wide use. The resulting resource consists of… (More)
We empirically show that there are significant differences between the discourse structure of Japanese texts and the discourse structure of their corresponding English translations. To improve translation quality, we propose a computational model for rewriting discourse structures. When we train our model on a parallel corpus of manually built Japanese and… (More)
We present discourse annotation work aimed at constructing a parallel corpus of Rhetorical Structure trees for a collection of Japanese texts and their corresponding English translations. We discuss implications of our empirical ndings for the task of text planning in the context of implementing multilingual natural language generation systems.
OBJECTIVE Cerebrospinal fluid (CSF) shunting can improve symptoms of elderly patients' idiopathic normal pressure hydrocephalus (iNPH). However, adjunctive means for confirming the diagnosis remain unavailable. We have previously reported the specific increase of leucine-rich alpha-2-glycoprotein (LRG) in iNPH CSF, and the present study investigates its… (More)
This paper presents a model for estimating the number of discarded products, taking sales mode differences into account. The model is constructed using actual copying machine collection data. The analysis of the data makes it clear that users who own and users who lease behave quite differently from each other, and that users who lease can be divided into… (More)
We present discourse annotation work aimed at constructing a parallel corpus of Rhetorical Structure trees for a collection of Japanese texts and their corresponding English translations. We discuss implications of our empirical findings for the task of text planning in the context of implementing multilingual natural language generation systems.