Amazon.com

About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Computer science & Service (business). The organization has 13363 authors who have published 17317 publications receiving 266589 citations.

DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning

Abstract: Misinformation such as fake news is one of the big challenges of our society. Research on automated fact-checking has proposed methods based on supervised learning, but these approaches do not consider external evidence apart from labeled training instances. Recent approaches counter this deficit by considering external sources related to a claim. However, these methods require substantial feature modeling and rich lexicons. This paper overcomes these limitations of prior work with an end-to-end model for evidence-aware credibility assessment of arbitrary textual claims, without any human intervention. It presents a neural network model that judiciously aggregates signals from external evidence articles, the language of these articles and the trustworthiness of their sources. It also derives informative features for generating user-comprehensible explanations that makes the neural network predictions transparent to the end-user. Experiments with four datasets and ablation studies show the strength of our method.

IL-17 mediates articular hypernociception in antigen-induced arthritis in mice.

Abstract: IL-17 is an important cytokine in the physiopathology of rheumatoid arthritis (RA). However, its participation in the genesis of nociception during RA remains undetermined. In this study, we evaluated the role of IL-17 in the genesis of articular nociception in a model of antigen (mBSA)-induced arthritis. We found that mBSA challenge in the femur-tibial joint of immunized mice induced a dose- and time-dependent mechanical hypernociception. The local IL-17 concentration within the mBSA-injected joints increased significantly over time. Moreover, co-treatment of mBSA challenged mice with an antibody against IL-17 inhibited hypernociception and neutrophil recruitment. In agreement, intraarticular injection of IL-17 induced hypernociception and neutrophil migration, which were reduced by the pre-treatment with fucoidin, a leukocyte adhesion inhibitor. The hypernociceptive effect of IL-17 was also reduced in TNFR1(-/-) mice and by pre-treatment with infliximab (anti-TNF antibody), a CXCR1/2 antagonist or by an IL-1 receptor antagonist. Consistent with these findings, we found that IL-17 injection into joints increased the production of TNF-alpha, IL-1beta and CXCL1/KC. Treatment with doxycycline (non-specific MMPs inhibitor), bosentan (ET(A)/ET(B) antagonist), indomethacin (COX inhibitor) or guanethidine (sympathetic blocker) inhibited IL-17-induced hypernociception. IL-17 injection also increased PGE(2) production, MMP-9 activity and COX-2, MMP-9 and PPET-1 mRNA expression in synovial membrane. These results suggest that IL-17 is a novel pro-nociceptive cytokine in mBSA-induced arthritis, whose effect depends on both neutrophil migration and various pro-inflammatory mediators, as TNF-alpha, IL-1beta, CXCR1/2 chemokines ligands, MMPs, endothelins, prostaglandins and sympathetic amines. Therefore, it is reasonable to propose IL-17 targeting therapies to control this important RA symptom.

Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation

Abstract: The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new capability: lexically constrained or guided decoding, a modification to beam search that forces the inclusion of pre-specified words and phrases in the output. However, while theoretically sound, existing approaches have computational complexities that are either linear (Hokamp and Liu, 2017) or exponential (Anderson et al., 2017) in the number of constraints. We present a algorithm for lexically constrained decoding with a complexity of O(1) in the number of constraints. We demonstrate the algorithm’s remarkable ability to properly place these constraints, and use it to explore the shaky relationship between model and BLEU scores. Our implementation is available as part of Sockeye.

System and method for exposing popular categories of browse tree

Abstract: A computer-implemented process identifies popular nodes (items and/or item categories) within a browse tree or other hierarchial browse structure based on historical actions of online users, and calls such nodes to the attention of users during navigation of the browse tree. The system and method are particularly useful for assisting users in locating popular products and/or product categories within a catalog on an online merchant, but may be used with browse structures for navigating other types of content. Node popularity levels are determined periodically (e.g. once per day) based on recent user activity data that reflects users' affinities for specific nodes. Popular nodes are called to the attention of users, preferably by automatically “elevating” such nodes for display within the browse tree. The node elevation process may also be used to elevate nodes that are predicted to be of interest to a user, regardless of node popularity levels.

Multi-style Generative Network for Real-time Transfer

Abstract: Despite the rapid progress in style transfer, existing approaches using feed-forward generative network for multi-style or arbitrary-style transfer are usually compromised of image quality and model flexibility. We find it is fundamentally difficult to achieve comprehensive style modeling using 1-dimensional style embedding. Motivated by this, we introduce CoMatch Layer that learns to match the second order feature statistics with the target styles. With the CoMatch Layer, we build a Multi-style Generative Network (MSG-Net), which achieves real-time performance. We also employ an specific strategy of upsampled convolution which avoids checkerboard artifacts caused by fractionally-strided convolution. Our method has achieved superior image quality comparing to state-of-the-art approaches. The proposed MSG-Net as a general approach for real-time style transfer is compatible with most existing techniques including content-style interpolation, color-preserving, spatial control and brush stroke size control. MSG-Net is the first to achieve real-time brush-size control in a purely feed-forward manner for style transfer. Our implementations and pre-trained models for Torch, PyTorch and MXNet frameworks will be publicly available.