Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and di
verse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by human and intrinsic evaluation. We fine-tune mT5, a state-of-the-art pretrained multilingual model, with XL-Sum and experiment on multilingual and low-resource summarization tasks. XL-Sum induces competitive results compared to the ones obtained using similar monolingual datasets: we show higher than 11 ROUGE-2 scores on 10 languages we benchmark on, with some of them exceeding 15, as obtained by multilingual training. Additionally, training on low-resource languages individually also provides competitive performance. To the best of our knowledge, XL-Sum is the largest abstractive summarization dataset in terms of the number of samples collected from a single source and the number of languages covered. We are releasing our dataset and models to encourage future research on multilingual abstractive summarization. The resources can be found at url{https://github.com/csebuetnlp/xl-sum}.
A Chatbot is a popular platform to enable users to interact with a software or website to gather information or execute actions in an automated fashion. In recent years, chatbots are being used for executing financial transactions, however, there are
a number of security issues, such as secure authentication, data integrity, system availability and transparency, that must be carefully handled for their wide-scale adoption. Recently, the blockchain technology, with a number of security advantages, has emerged as one of the foundational technologies with the potential to disrupt a number of application domains, particularly in the financial sector. In this paper, we forward the idea of integrating a chatbot with blockchain technology in the view to improve the security issues in financial chatbots. More specifically, we present BONIK, a blockchain empowered chatbot for financial transactions, and discuss its architecture and design choices. Furthermore, we explore the developed Proof-of-Concept (PoC), evaluate its performance, analyse how different security and privacy issues are mitigated using BONIK.
In this paper, we present an approach for identification of actions within depth action videos. First, we process the video to get motion history images (MHIs) and static history images (SHIs) corresponding to an action video based on the use of 3D M
otion Trail Model (3DMTM). We then characterize the action video by extracting the Gradient Local Auto-Correlations (GLAC) features from the SHIs and the MHIs. The two sets of features i.e., GLAC features from MHIs and GLAC features from SHIs are concatenated to obtain a representation vector for action. Finally, we perform the classification on all the action samples by using the l2-regularized Collaborative Representation Classifier (l2-CRC) to recognize different human actions in an effective way. We perform evaluation of the proposed method on three action datasets, MSR-Action3D, DHA and UTD-MHAD. Through experimental results, we observe that the proposed method performs superior to other approaches.
First principles density functional theory (DFT) is used to investigate the electronic structure of beta-MnO2. From collinear spin polarized calculations we find that DFT+U_Eff predicts a gapless ferromagnet in contrast with experiment which indicate
s an insulating antiferromagnet. The inclusion of anisotropic Coulomb and exchange interactions in the DFT+U approach, defining U and J explicitly, corrects these errors and leads to an antiferromagnetic ground state with a fundamental gap of 0.8 eV consistent with low temperature experiments. To our knowledge, this work on beta-MnO2 represents the first demonstration of a case in which the application of fully anisotropic interactions in DFT+U determines the magnetic order and consequent band gap, while the more commonly used effective U approach fails. Such effects are argued to be of importance in many insulating materials. The mechanism leading to an increase in band gap due to anisotropic interactions is highlighted by analytical calculation of DFT+U d-orbital eigenvalues obtained within a Kanamori-type model. Magnetic coupling constants obtained by the fitting of a Heisenberg spin Hamiltonian to the energies of a range of magnetic states assist in rationalizing the finding that anisotropic interactions enhance the stability of the experimentally observed helical antiferromagnetic order. The plane wave PAW method yields poorer results for the exchange couplings than full-potential LAPW calculations. Finally, we compare the DFT+U results with exchange couplings obtained from hybrid functionals. It is argued that anisotropic interactions should be included in DFT+U if the results are to be properly compared with those from hybrid functionals.
