Joint extraction of entities and relations from unstructured texts is a crucial task in information extraction. Recent methods achieve considerable performance but still suffer from some inherent limitations, such as redundancy of relation prediction, poor generalization of span-based extraction and inefficiency. In this paper, we decompose this task into three subtasks, Relation Judgement, Entity Extraction and Subject-object Alignment from a novel perspective and then propose a joint relational triple extraction framework based on Potential Relation and Global Correspondence (PRGC). Specifically, we design a component to predict potential relations, which constrains the following entity extraction to the predicted relation subset rather than all relations; then a relation-specific sequence tagging component is applied to handle the overlapping problem between subjects and objects; finally, a global correspondence component is designed to align the subject and object into a triple with low-complexity. Extensive experiments show that PRGC achieves state-of-the-art performance on public benchmarks with higher efficiency and delivers consistent performance gain on complex scenarios of overlapping triples.
Understanding the unique behaviors
of atomically dispersed catalysts
and the origin thereof is a challenging topic. Herein, we demonstrate
a facile strategy to encapsulate Ptδ+ species within
Y zeolite and reveal the nature of selective hydrogenation over a
Pt@Y model catalyst. The unique configuration of Pt@Y, namely atomically
dispersed Ptδ+ stabilized by the surrounding oxygen
atoms of six-membered rings shared by sodalite cages and supercages,
enables the exclusive heterolytic activation of dihydrogen over Ptδ+···O2– units, resembling
the well-known classical Lewis pairs. The charged hydrogen species,
i.e., H+ and Hδ−, are active reagents
for selective hydrogenations, and therefore, the Pt@Y catalyst exhibits
remarkable performance in the selective hydrogenation of α,β-unsaturated
aldehydes to unsaturated alcohols and of nitroarenes to arylamines.
Epilepsy is a neurological illness caused by abnormal discharge of brain neurons, where epileptic seizure can lead to life-threatening emergencies. By analyzing the encephalogram (EEG) signals of patients with epilepsy, their conditions can be monitored and seizure can be detected and intervened in time. As the identification of effective features in EEG signals is important for accurate seizure detection, this paper proposes a multi-view deep feature extraction method in attempt to achieve this goal. The method first uses fast Fourier transform (FFT) and wavelet packet decomposition (WPD) to construct the initial multi-view features. Convolutional neural network (CNN) is then used to automatically learn deep features from the initial multi-view features, which reduces the dimensionality and obtain the features with better seizure identification ability. Furthermore, the multi-view Takagi-Sugeno-Kang fuzzy system (MV-TSK-FS), an interpretable rule-based classifier, is used to construct a classification model with strong generalizability based on the deep multi-view features obtained. Experimental studies show that the classification accuracy of the proposed multi-view deep feature extraction method is at least 1% higher than that of common feature extraction methods such as principal component analysis (PCA), FFT and WPD. The classification accuracy is also at least 4% higher than the average accuracy achieved with single-view deep features.
a b s t r a c tA series of chitosan bis(methylphenylcarbamate)-(isobutyrylamide) derivatives were synthesized by carbamylating chitosan isobutyrylamide with different methylphenyl isocyanates. Then the prepared chitosan derivatives were coated onto 3-aminopropyl silica particles, resulting in a series of new chiral stationary phases (CSPs) for high-performance liquid chromatography. It was observed that the chiral recognition abilities of these coated-type CSPs depended very much on the substituents on the phenyl moieties of the chitosan derivatives, the eluent composition, as well as the structure of racemates. As a typical example, the eluent tolerance of the prepared CSP with the best enantioseparation ability was investigated in detail, and the results revealed that the CSP exhibited extraordinary solvent tolerance and could still work without significant loss in enantioseparation capability after being flushed with chloroform (100%), ethyl acetate (100%) and even THF/n-hexane (70/30, v/v), while the traditional coated-type CSPs based on the cellulose and amylose derivatives, such as cellulose tris(3,5-dimethylphenylcarbamate) (CDMPC) and amylose tris(3,5-dimethylphenylcarbamate) (ADMPC), might be dissolved or highly swollen in these eluents. Therefore, the application of the resultant CSPs could address the problem of the dissolution and high swelling of traditional coated-type CSPs in some unusual eluents, broadening the possibility of eluent choice. In addition, a comparison of the prepared CSPs with the well known CDMPC-and ADMPC-based CSPs concerning the chiral recognition ability was also made. Separation performances achieved on the as-prepared CSPs in different eluents were found to be even superior to CDMPC-and ADMPC-based CSPs for the tested chiral compounds. In summary, we could safely draw the conclusion that the CSPs derived from chitosan isobutyrylamide derivatives were capable of excellent chiral recognition ability, and meanwhile possessed satisfactory eluent tolerance in a wider range of solvents.
Face recognition has been an active and vital topic among computer vision community for a long time. Previous researches mainly focus on loss functions used for facial feature extraction network, among which the improvements of softmax-based loss functions greatly promote the performance of face recognition. However, the contradiction between the drastically increasing number of face identities and the shortage of GPU memories is gradually becoming irreconcilable. In this paper, we thoroughly analyze the optimization goal of softmax-based loss functions and the difficulty of training massive identities. We find that the importance of negative classes in softmax function in face representation learning is not as high as we previously thought. The experiment demonstrates no loss of accuracy when training with only 10% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks. We also implement a very efficient distributed sampling algorithm, taking into account model accuracy and training efficiency, which uses only eight NVIDIA RTX2080Ti to complete classification tasks with tens of millions of identities. The code of this paper has been made available https://github.com/ deepinsight/insightface/tree/master/recognition/partial fc.
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.