Learn More
Developing a full coreference system able to run all the way from raw text to semantic interpretation is a considerable engineering effort, yet there is very limited availability of off-the shelf tools for researchers whose interests are not in coreference, or for researchers who want to concentrate on a specific aspect of the problem. We present BART, a(More)
In this paper we propose a competition learning approach to coreference resolution. Traditionally, supervised machine learning approaches adopt the single-candidate model. Nevertheless the preference relationship between the antecedent candidates cannot be determined accurately in this model. By contrast, our approach adopts a twin-candidate learning model.(More)
Leptin is a hormone that reduces excitability in some hypothalamic neurons via leptin receptor activation of the JAK2 and PI3K intracellular signaling pathways. We hypothesized that leptin receptor activation in other neuronal subtypes would have anticonvulsant activity and that intranasal leptin delivery would be an effective route of administration. We(More)
The traditional mention-pair model for coref-erence resolution cannot capture information beyond mention pairs for both learning and testing. To deal with this problem, we present an expressive entity-mention model that performs coreference resolution at an entity level. The model adopts the Inductive Logic Programming (ILP) algorithm, which provides a(More)
Although hyperhomocysteinemia is an independent risk factor for cardiovascular disease, a direct role for homocysteine (Hcy) in this disease remains to be shown. Whereas diet-induced hyperhomocysteinemia promotes atherosclerosis in animal models, the effects of Hcy on atherogenesis in the absence of dietary perturbations is not known. We have generated(More)
In this paper we present a noun phrase coreference resolution system which aims to enhance the identification of the coreference realized by string matching. For this purpose, we make two extensions to the standard learning based resolution framework. First, to improve the recall rate, we introduce an additional set of features to capture the different(More)
Cordycepin (Cor), which is a naturally occurring nucleoside derivative isolated from Cordyceps militaris, has been shown to exert excellent antiinflammatory activity in a murine model of acute lung injury. Thus, this study aimed to evaluate the antiasthmatic activity of Cor (10, 20, and 40 mg/kg) and to investigate the possible underlying molecular(More)
Background and objective Combined magnetic resonance/positron emission tomography (MR/PET) is a relatively new, hybrid imaging modality. MR-based attenuation correction often requires segmentation of the bone on MR images. In this study, we present an automatic segmentation method for the skull on MR images for attenuation correction in brain MR/PET(More)
Syntactic knowledge is important for pronoun resolution. Traditionally, the syntactic information for pronoun resolution is represented in terms of features that have to be selected and defined heuristically. In the paper, we propose a kernel-based method that can automatically mine the syntactic information from the parse trees for pronoun resolution.(More)