Comprehensive summary of the progress including crystal structures, fabrication methods, applications (especially for electronics) and functionalization of 2D-hBN from its discovery.

Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.

The perovskite solar cell has emerged rapidly in the field of photovoltaics as it combines the merits of low cost, high efficiency, and excellent mechanical flexibility for versatile applications. However, there are significant concerns regarding its operational stability and mechanical robustness. Most of the previously reported approaches to address these concerns entail separate engineering of perovskite and charge-transporting layers. Herein we present a holistic design of perovskite and charge-transporting layers by synthesizing an interpenetrating perovskite/electron-transporting-layer interface. This interface is reaction-formed between a tin dioxide layer containing excess organic halide and a perovskite layer containing excess lead halide. Perovskite solar cells with such interfaces deliver efficiencies up to 22.2% and 20.1% for rigid and flexible versions, respectively. Long-term (1000 h) operational stability is demonstrated and the flexible devices show high endurance against mechanical-bending (2500 cycles) fatigue. Mechanistic insights into the relationship between the interpenetrating interface structure and performance enhancement are provided based on comprehensive, advanced, microscopic characterizations. This study highlights interface integrity as an important factor for designing efficient, operationally-stable, and mechanically-robust solar cells.

We propose a novel multi-grained attention network (MGAN) model for aspect level sentiment classification. Existing approaches mostly adopt coarse-grained attention mechanism, which may bring information loss if the aspect has multiple words or larger context. We propose a fine-grained attention mechanism, which can capture the word-level interaction between aspect and context. And then we leverage the fine-grained and coarsegrained attention mechanisms to compose the MGAN framework. Moreover, unlike previous works which train each aspect with its context separately, we design an aspect alignment loss to depict the aspect-level interactions among the aspects that have the same context. We evaluate the proposed approach on three datasets: laptop and restaurant are from SemEval 2014, and the last one is a twitter dataset. Experimental results show that the multi-grained attention network consistently outperforms the state-of-the-art methods on all three datasets. We also conduct experiments to evaluate the effectiveness of aspect alignment loss, which indicates the aspect-level interactions can bring extra useful information and further improve the performance.