Leveraging external knowledge is an emerging trend in machine comprehension task. Previous work usually utilizes knowledge graphs such as ConceptNet as external knowledge, and extracts triples from them to enhance the initial representation of the machine comprehension context. However, such method cannot capture the structural information in the knowledge graph. To this end, we propose a Structural Knowledge Graph-aware Network (SKG) model, constructing sub-graphs for entities in the machine comprehension context. Our method dynamically updates the representation of the knowledge according to the structural information of the constructed sub-graph. Experiments show that SKG achieves state-ofthe-art performance on the ReCoRD dataset.
Citrus fruits are major agricultural products of China and they are rich sources of health beneficial substances. In this study, Raman spectroscopy as a rapid and non-destructive tool was employed to classify eight different citrus fruits. Baseline drift caused by fluorescence of organic compounds in the citrus samples interferes with the Raman signals. A polynomial fitting based method was adopted for baseline correction, which is a key factor both for Raman peaks assignment and subsequent pattern recognition. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) were the two selected pattern recognition techniques. PCA showed the distribution of sweet oranges and mandarins, and HCA was a useful guide for detailed relationship between various citrus samples. The results demonstrated that Raman spectroscopy combined with pattern recognition techniques has substantial potential for discriminating varieties of citrus fruits.
Citrus fruits are of great interest because they contain flavonoids which are health promoting substances. Hesperidin, nobiletin and tangeretin are flavonoid glycosides that occur naturally in citrus. In the present study, a reversed-phase high-performance liquid chromatographic method has been developed for the rapid separation and determination of hesperidin, nobiletin and tangeretin in different fresh citrus fruit juices and commercial citrus beverages. Furthermore, principal component analysis was applied to their chromatographic profiles. Classification of orange, mandarin and hybrid was achieved. The possibility of estimating the approximate juice content of commercial beverages based on their PC1 values was attempted. These results demonstrated that the combination of HPLC and chemometrics offers a feasible and efficient approach for quality evaluation of citrus fruits and beverages.
This paper focuses on the answer sentence selection task. Unlike previous work, which only models the relation between the question and each candidate sentence, we propose Multi-Perspective Graph Encoder (MPGE) to take the relations among the candidate sentences into account and capture the relations from multiple perspectives. By utilizing MPGE as a module, we construct two answer sentence selection models which are based on traditional representation and pre-trained representation, respectively. We conduct extensive experiments on two datasets, WikiQA and SQuAD. The results show that the proposed MPGE is effective for both types of representation. Moreover, the overall performance of our proposed model surpasses the state-of-the-art on both datasets. Additionally, we further validate the robustness of our method by the adversarial examples of AddSent and AddOneSent.
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.