health reform is the outcome of dispersed policy initiatives in different sectors, at different levels and across time. policy work which can drive coherent health reform needs to operate across the governance structures as well as the institutions that comprise healthcare systems. building policy capacity to support health reform calls for clarity regarding the nature of such policy work and t...

Wei Wei, Etienne Barnard and Mark Fanty Center for Spoken Language Understanding Oregon Graduate Institute of Science and Technology 20000 N.W.Walker Road, Portland, OR 97291-1000 ABSTRACT Neural network classi ers can provide outputs that estimate Bayesian posterior probabilities under the assumptions that an in nite amount of training data are available, the network is su ciently complex and ...

Cloze test is widely adopted in language exams to evaluate students’ language proficiency. In this paper, we propose the first large-scale human-designed cloze test dataset CLOTH 1, in which the questions were used in middle-school and high-school language exams. With the missing blanks carefully created by teachers and candidate choices purposely designed to be confusing, CLOTH requires a deep...

In previous papers we have argued for the complete integration of natural language understanding with the rest of the cognitive system. Given a set of richly indexed memory structures, we have claimed that parsing is a general memory search process guided by predictive patterns of lexical and conceptual items which are a part of those memory structures. In this paper, we demonstrate that our ar...

Segmentation of perivascular spaces (PVS) from brain magnetic resonance images (MRI) is important for understanding the brain’s lymphatic system and its relationship with neurological diseases. The Frangi filter might be a valuable tool for this purpose. However, its parameters need to be adjusted in response to the variability in scanner’s parameters and study protocols. Knowing the neuroradio...

We have participated in the Multilingual Entity Task (MET) for Japanese and Spanish using SRA's multilingual text-indexing software called NameTag TM. Its English version was used for the Named Entity Task (NE) in MUC-6 [2]. The NameTag Japanese and Spanish systems were customized to accommodate the MET-specific requirements and were able to achieve high performance in both recall and precision.

The use of logic for knowledge representation and reasoning systems is controversial. There are, indeed, several ways that standard First Order Predicate Logic is inappropriate for modelling natural language understanding and commonsense reasoning. However, a more appropriate logic can be designed. This paper presents several aspects of such a logic.

In human robot dialogue, identifying intended referents from human partners’ spatial language is challenging. This is partly due to automated inference of potentially ambiguous underlying reference system (i.e., frame of reference). To improve spatial language understanding, we conducted an empirical study to investigate the prevalence of ambiguities of frame of reference. Our findings indicate...

Statistical Language Understanding Using Frame Semantics