Institution
Amazon.com
Company•Seattle, Washington, United States•
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.
Topics: Computer science, Service (business), Service provider, Context (language use), Virtual machine
Papers published on a yearly basis
Papers
More filters
•
19 Jun 2016TL;DR: A robust random cut data structure that can be used as a sketch or synopsis of the input stream is investigated and it is shown how the sketch can be efficiently updated in a dynamic data stream.
Abstract: In this paper we focus on the anomaly detection problem for dynamic data streams through the lens of random cut forests. We investigate a robust random cut data structure that can be used as a sketch or synopsis of the input stream. We provide a plausible definition of non-parametric anomalies based on the influence of an unseen point on the remainder of the data, i.e., the externality imposed by that point. We show how the sketch can be efficiently updated in a dynamic data stream. We demonstrate the viability of the algorithm on publicly available real data.
190 citations
•
31 Aug 2017TL;DR: The experiments show that transfer learning helps word-based translation only slightly, but when used on top of a much stronger BPE baseline, it yields larger improvements of up to 4.3 BLEU.
Abstract: We present a simple method to improve neural translation of a low-resource language pair using parallel data from a related, also low-resource, language pair. The method is based on the transfer method of Zoph et al., but whereas their method ignores any source vocabulary overlap, ours exploits it. First, we split words using Byte Pair Encoding (BPE) to increase vocabulary overlap. Then, we train a model on the first language pair and transfer its parameters, including its source word embeddings, to another model and continue training on the second language pair. Our experiments show that transfer learning helps word-based translation only slightly, but when used on top of a much stronger BPE baseline, it yields larger improvements of up to 4.3 BLEU.
189 citations
•
30 Nov 2005TL;DR: In this article, a piece of content is automatically assessed in a manner based on automatically assessed levels of trust in users who are associated with the content, such as a user who authored or otherwise supplied the content and/or users who evaluated the content.
Abstract: Techniques are described for managing content by identifying content that has attributes of interest (e.g., content that is useful, humorous and/or that otherwise has a sufficiently high degree of quality) and by determining how to use such identified content. In some situations, a piece of content is automatically assessed in a manner based on automatically assessed levels of trust in users who are associated with the content, such as a user who authored or otherwise supplied the content and/or users who evaluated the content. For example, an automatically assessed level of trust for a user may be based on prior activities of the user and be used to predict future behavior of the user as a supplier of acceptable content and/or as an acceptable evaluator of supplied content, such as based on prior activities of the user that are not related to supplying and/or evaluating content.
188 citations
••
01 Aug 2017
TL;DR: In this article, the authors combine deep learning with active learning and show that they can outperform classical methods even with a significantly smaller amount of training data than a large dataset or a large budget for manually labeling data.
Abstract: Deep neural networks have advanced the state of the art in named entity recognition. However, under typical training procedures, advantages over classical methods emerge only with large datasets. As a result, deep learning is employed only when large public datasets or a large budget for manually labeling data is available. In this work, we show otherwise: by combining deep learning with active learning, we can outperform classical methods even with a significantly smaller amount of training data.
188 citations
••
Conservation International1, Wildlife Conservation Society2, Duke University3, Wageningen University and Research Centre4, University of Nottingham Malaysia Campus5, Pontificia Universidad Católica del Ecuador6, Forest Research Institute Malaysia7, Organization for Tropical Studies8, Smithsonian Tropical Research Institute9, Hewlett-Packard10, Federal University of Pará11, Mbarara University of Science and Technology12, Universidad Yachay Tech13, University of Florida14, Norwegian University of Life Sciences15, Amazon.com16, University of Connecticut17, University of Indonesia18
TL;DR: Evaluating occupancy trends for 511 populations of terrestrial mammals and birds, representing 244 species from 15 tropical forest protected areas on three continents, finds that occupancy declined in 22, increased in 17%, and exhibited no change in 22% of populations during the last 3–8 years, while 39% of population were detected too infrequently to assess occupancy changes.
Abstract: Extinction rates in the Anthropocene are three orders of magnitude higher than background and disproportionately occur in the tropics, home of half the world’s species. Despite global efforts to combat tropical species extinctions, lack of high-quality, objective information on tropical biodiversity has hampered quantitative evaluation of conservation strategies. In particular, the scarcity of population-level monitoring in tropical forests has stymied assessment of biodiversity outcomes, such as the status and trends of animal populations in protected areas. Here, we evaluate occupancy trends for 511 populations of terrestrial mammals and birds, representing 244 species from 15 tropical forest protected areas on three continents. For the first time to our knowledge, we use annual surveys from tropical forests worldwide that employ a standardized camera trapping protocol, and we compute data analytics that correct for imperfect detection. We found that occupancy declined in 22%, increased in 17%, and exhibited no change in 22% of populations during the last 3–8 years, while 39% of populations were detected too infrequently to assess occupancy changes. Despite extensive variability in occupancy trends, these 15 tropical protected areas have not exhibited systematic declines in biodiversity (i.e., occupancy, richness, or evenness) at the community level. Our results differ from reports of widespread biodiversity declines based on aggregated secondary data and expert opinion and suggest less extreme deterioration in tropical forest protected areas. We simultaneously fill an important conservation data gap and demonstrate the value of large-scale monitoring infrastructure and powerful analytics, which can be scaled to incorporate additional sites, ecosystems, and monitoring methods. In an era of catastrophic biodiversity loss, robust indicators produced from standardized monitoring infrastructure are critical to accurately assess population outcomes and identify conservation strategies that can avert biodiversity collapse.
188 citations
Authors
Showing all 13498 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jiawei Han | 168 | 1233 | 143427 |
Bernhard Schölkopf | 148 | 1092 | 149492 |
Christos Faloutsos | 127 | 789 | 77746 |
Alexander J. Smola | 122 | 434 | 110222 |
Rama Chellappa | 120 | 1031 | 62865 |
William F. Laurance | 118 | 470 | 56464 |
Andrew McCallum | 113 | 472 | 78240 |
Michael J. Black | 112 | 429 | 51810 |
David Heckerman | 109 | 483 | 62668 |
Larry S. Davis | 107 | 693 | 49714 |
Chris M. Wood | 102 | 795 | 43076 |
Pietro Perona | 102 | 414 | 94870 |
Guido W. Imbens | 97 | 352 | 64430 |
W. Bruce Croft | 97 | 426 | 39918 |
Chunhua Shen | 93 | 681 | 37468 |