Click-through rate (CTR) prediction, whose goal is to estimate the probability of a user clicking on the item, has become one of the core tasks in the advertising system. For CTR prediction model, it is necessary to capture the latent user interest behind the user behavior data. Besides, considering the changing of the external environment and the internal cognition, user interest evolves over time dynamically. There are several CTR prediction methods for interest modeling, while most of them regard the representation of behavior as the interest directly, and lack specially modeling for latent interest behind the concrete behavior. Moreover, little work considers the changing trend of the interest. In this paper, we propose a novel model, named Deep Interest Evolution Network (DIEN), for CTR prediction. Specifically, we design interest extractor layer to capture temporal interests from history behavior sequence. At this layer, we introduce an auxiliary loss to supervise interest extracting at each step. As user interests are diverse, especially in the e-commerce system, we propose interest evolving layer to capture interest evolving process that is relative to the target item. At interest evolving layer, attention mechanism is embedded into the sequential structure novelly, and the effects of relative interests are strengthened during interest evolution. In the experiments on both public and industrial datasets, DIEN significantly outperforms the state-of-the-art solutions. Notably,
We propose a new CogQA framework for multi-hop question answering in web-scale documents. Founded on the dual process theory in cognitive science, the framework gradually builds a cognitive graph in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2). While giving accurate answers, our framework further provides explainable reasoning paths. Specifically, our implementation 1 based on BERT and graph neural network (GNN) efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint F 1 score of 34.9 on the leaderboard, compared to 23.6 of the best competitor. 2
Until now, there is not yet antitumor drug with dramatically improved efficacy on non-small cell lung cancer (NSCLC). Marine organisms are rich source of novel compounds with various activities. We isolated stellettin B (Stel B) from marine sponge Jaspis stellifera, and demonstrated that it induced G1 arrest, apoptosis and autophagy at low concentrations in human NSCLC A549 cells. G1 arrest by Stel B might be attributed to the reduction of cyclin D1 and enhancement of p27 expression. The apoptosis induction might be related to the cleavage of PARP and increase of ROS generation. Moreover, we demonstrated that Stel B induced autophagy in A549 cells by use of various assays including monodansylcadaverine (MDC) staining, transmission electron microscopy (TEM), tandem mRFP-GFP-LC3 fluorescence microscopy, and western blot detection of the autophagy markers of LC3B, p62 and Atg5. Meanwhile, Stel B inhibited the expression of PI3K-p110, and the phosphorylation of PDK1, Akt, mTOR, p70S6K as well as GSK-3β, suggesting the correlation of blocking PI3K/Akt/mTOR pathway with the above antitumor activities. Together, our findings indicate the antitumor potential of Stel B for NSCLC by targeting PI3K/Akt/mTOR pathway.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.