Learn More
In this article we present Supervised Semantic Indexing which defines a class of nonlinear (quadratic) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score. Like Latent Semantic Indexing (LSI), our models take account of correlations between words (synonymy,(More)
BACKGROUND Brain imaging studies of early Alzheimer's disease (AD) have shown decreased metabolism predominantly in the posterior cingulate cortex (PCC), medial temporal lobe, and inferior parietal lobe. This study investigated functional connectivity between these regions, as well as connectivity between these regions and the whole brain. METHODS(More)
Expansion of a hexanucleotide repeat GGGGCC (G4C2) in C9ORF72 is the most common cause of amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD). Transcripts carrying (G4C2) expansions undergo unconventional, non-ATG-dependent translation, generating toxic dipeptide repeat (DPR) proteins thought to contribute to disease. Here, we identify the(More)
We present a class of nonlinear (polynomial) models that are discriminatively trained to directly map from the word content in a query-document or documentdocument pair to a ranking score. Dealing with polynomial models on word features is computationally challenging. We propose a low-rank (but diagonal preserving) representation of our polynomial models to(More)
Deposition of insoluble protein aggregates is a hallmark of neurodegenerative diseases. The universal presence of β-amyloid and tau in Alzheimer's disease (AD) has facilitated advancement of the amyloid cascade and tau hypotheses that have dominated AD pathogenesis research and therapeutic development. However, the underlying etiology of the disease remains(More)
In this paper, we propose an efficient embedding for modeling higher-order (n-gram) phrases that projects the n-grams to low-dimensional latent semantic space, where a classification function can be defined. We utilize a deep neural network to build a unified discriminative framework that allows for estimating the parameters of the latent space as well as(More)
The combination of gemcitabine (G), vinorelbine (V), and pegylated liposomal doxorubicin (D) has proved to be effective in relapsed Hodgkin's lymphoma (HL). Its efficacy in non-Hodgkin's lymphoma (NHL) remains to be discussed. We retrospectively evaluated the efficacy and toxicity of the dose-adjusted gemcitabine, vinorelbine, liposomal doxorubicin (GVD) in(More)
Activating mutations in Ras proteins are present in about 30% of human cancers. Despite tremendous progress in the study of Ras oncogenes, many aspects of the molecular mechanisms underlying Ras-induced tumorigenesis remain unknown. Through proteomics analysis, we previously found that the protein Gankyrin, a known oncoprotein in hepatocellular carcinoma,(More)