Learn More
Relation classification is an important research arena in the field of natural language processing (NLP). In this paper, we present SDP-LSTM, a novel neural network to classify the relation of two entities in a sentence. Our neural architecture leverages the shortest dependency path (SDP) between two entities; multichannel recurrent neural networks, with(More)
The miR-34 family members are direct transcriptional targets of tumor suppressor p53, and loss of miR-34 function can impair p53-mediated cell cycle arrest and apoptosis. A potentially functional SNP rs4938723 (T > C) was found in the promoter region of pri-miR-34b/c (423 bp from the transcription start site), located in the CpG island and might affect(More)
In this paper, we propose the TBCNNpair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentencelevel semantics; then heuristic matching layers like concatenation, element-wise product/difference combine the information in individual sentences. Experimental(More)
To investigate the association between the potentially functional polymorphisms in IL12A and IL12B, HBV infection and risk of hepatocellular carcinoma in a Chinese population, we genotyped three polymorphisms, rs568408 (3'UTR G>A), rs2243115 (5'UTR T>G) in IL12A and rs3212227 (3'UTR A>C) in IL12B in a case-control study of 869 hepatocellular carcinoma (HCC)(More)
Netrins are secreted proteins that regulate axon guidance and neuronal migration. Deleted in colorectal cancer (DCC) is a well-established netrin-1 receptor mediating attractive responses. We provide evidence that its close relative neogenin is also a functional netrin-1 receptor that acts with DCC to mediate guidance in vivo. We determined the structures(More)
Technology-based interventions for promoting health behavior-change frequently leverage multiplayer game mechanics such as group-based competitions. However, health interventions successful for groups writ large may not always translate to successful behavior change at the individual level. In this paper, we explore the tension between group and individual(More)
This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling. Our model leverages either constituency trees or dependency trees of sentences. The tree-based convolution process extracts sentences structural features, which are then aggregated by max pooling. Such architecture allows short propagation paths(More)
UNLABELLED Single nucleotide polymorphisms (SNPs) are the most abundant form of genetic variations in closely related microbial species, strains or isolates. Some SNPs confer selective advantages for microbial pathogens during infection and many others are powerful genetic markers for distinguishing closely related strains or isolates that could not be(More)
Insulin-like growth factor 1 (IGF1) and its main binding protein, IGF-binding protein 3 (IGFBP3), play an important role in cancer development. Circulating levels and functional polymorphisms of IGF1 and IGFBP3 may be biomarkers of cancer development. However, the results of published studies remain conflicting rather than conclusive. We searched MEDLINE(More)
Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain. It is particularly important to neural networks, which are very likely to be overfitting. In some fields like image processing, many studies have shown the effectiveness of neural network-based transfer learning. For neural NLP,(More)