Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExtracting Scientific Figures with Distantly Supervised Neural Networks
232
0
0.0
(
0
)
Added by
Noah Siegel
Publication date
2018
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Non-textual components such as charts, diagrams and tables provide key information in many scientific documents, but the lack of large labeled datasets has impeded the development of data-driven methods for scientific figure extraction. In this paper, we induce high-quality training labels for the task of figure extraction in a large number of scientific documents, with no human intervention. To accomplish this we leverage the auxiliary data provided in two large web collections of scientific documents (arXiv and PubMed) to locate figures and their associated captions in the rasterized PDF. We share the resulting dataset of over 5.5 million induced labels---4,000 times larger than the previous largest figure extraction dataset---with an average precision of 96.8%, to enable the development of modern data-driven methods for this task. We use this dataset to train a deep neural network for end-to-end figure detection, yielding a model that can be more easily extended to new domains compared to previous work. The model was successfully deployed in Semantic Scholar, a large-scale academic search engine, and used to extract figures in 13 million scientific documents.
rate research
Read More
We provide an up-to-date view on the knowledge management system ScienceWISE (SW) and address issues related to the automatic assignment of articles to research topics. So far, SW has been proven to be an effective platform for managing large volumes of technical articles by means of ontological concept-based browsing. However, as the publication of research articles accelerates, the expressivity and the richness of the SW ontology turns into a double-edged sword: a more fine-grained characterization of articles is possible, but at the cost of introducing more spurious relations among them. In this context, the challenge of continuously recommending relevant articles to users lies in tackling a network partitioning problem, where nodes represent articles and co-occurring concepts create edges between them. In this paper, we discuss the three research directions we have taken for solving this issue: i) the identification of generic concepts to reinforce inter-article similarities; ii) the adoption of a bipartite network representation to improve scalability; iii) the design of a clustering algorithm to identify concepts for cross-disciplinary articles and obtain fine-grained topics for all articles.
Convolutional neural networks (CNNs) have proven to be highly successful at a range of image-to-image tasks. CNNs can be computationally expensive, which can limit their applicability in practice. Model pruning can improve computational efficiency by sparsifying trained networks. Common methods for pruning CNNs determine what convolutional filters to remove by ranking filters on an individual basis. However, filters are not independent, as CNNs consist of chains of convolutions, which can result in sub-optimal filter selection. We propose a novel pruning method, LongEst-chAiN (LEAN) pruning, which takes the interdependency between the convolution operations into account. We propose to prune CNNs by using graph-based algorithms to select relevant chains of convolutions. A CNN is interpreted as a graph, with the operator norm of each convolution as distance metric for the edges. LEAN pruning iteratively extracts the highest value path from the graph to keep. In our experiments, we test LEAN pruning for several image-to-image tasks, including the well-known CamVid dataset. LEAN pruning enables us to keep just 0.5%-2% of the convolutions without significant loss of accuracy. When pruning CNNs with LEAN, we achieve a higher accuracy than pruning filters individually, and different pruned substructures emerge.
We consider using {bfem untrained neural networks} to solve the reconstruction problem of snapshot compressive imaging (SCI), which uses a two-dimensional (2D) detector to capture a high-dimensional (usually 3D) data-cube in a compressed manner. Various SCI systems have been built in recent years to capture data such as high-speed videos, hyperspectral images, and the state-of-the-art reconstruction is obtained by the deep neural networks. However, most of these networks are trained in an end-to-end manner by a large amount of corpus with sometimes simulated ground truth, measurement pairs. In this paper, inspired by the untrained neural networks such as deep image priors (DIP) and deep decoders, we develop a framework by integrating DIP into the plug-and-play regime, leading to a self-supervised network for spectral SCI reconstruction. Extensive synthetic and real data results show that the proposed algorithm without training is capable of achieving competitive results to the training based networks. Furthermore, by integrating the proposed method with a pre-trained deep denoising prior, we have achieved state-of-the-art results. {Our code is available at url{https://github.com/mengziyi64/CASSI-Self-Supervised}.}
The vast and growing number of publications in all disciplines of science cannot be comprehended by a single human researcher. As a consequence, researchers have to specialize in narrow sub-disciplines, which makes it challenging to uncover scientific connections beyond the own field of research. Thus access to structured knowledge from a large corpus of publications could help pushing the frontiers of science. Here we demonstrate a method to build a semantic network from published scientific literature, which we call SemNet. We use SemNet to predict future trends in research and to inspire new, personalized and surprising seeds of ideas in science. We apply it in the discipline of quantum physics, which has seen an unprecedented growth of activity in recent years. In SemNet, scientific knowledge is represented as an evolving network using the content of 750,000 scientific papers published since 1919. The nodes of the network correspond to physical concepts, and links between two nodes are drawn when two physical concepts are concurrently studied in research articles. We identify influential and prize-winning research topics from the past inside SemNet thus confirm that it stores useful semantic knowledge. We train a deep neural network using states of SemNet of the past, to predict future developments in quantum physics research, and confirm high quality predictions using historic data. With the neural network and theoretical network tools we are able to suggest new, personalized, out-of-the-box ideas, by identifying pairs of concepts which have unique and extremal semantic network properties. Finally, we consider possible future developments and implications of our findings.
With recent advances in distantly supervised (DS) relation extraction (RE), considerable attention is attracted to leverage multi-instance learning (MIL) to distill high-quality supervision from the noisy DS. Here, we go beyond label noise and identify the key bottleneck of DS-MIL to be its low data utilization: as high-quality supervision being refined by MIL, MIL abandons a large amount of training instances, which leads to a low data utilization and hinders model training from having abundant supervision. In this paper, we propose collaborative adversarial training to improve the data utilization, which coordinates virtual adversarial training (VAT) and adversarial training (AT) at different levels. Specifically, since VAT is label-free, we employ the instance-level VAT to recycle instances abandoned by MIL. Besides, we deploy AT at the bag-level to unleash the full potential of the high-quality supervision got by MIL. Our proposed method brings consistent improvements (~ 5 absolute AUC score) to the previous state of the art, which verifies the importance of the data utilization issue and the effectiveness of our method.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
