Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vectorspace representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a word-level baseline at predicting user-annotated hashtags associated with the posts, doing significantly better when the input contains many outof-vocabulary words or unusual character sequences. Our tweet2vec encoder is publicly available 1 .

Thermodynamically favorable electrooxidation reactions of biomass derivatives integrated with hydrogen evolution reaction (HER) can simultaneously provide value‐added chemicals and hydrogen, and eventually meeting the need for clean and sustainable energy development. Herein, the integration of a six‐electron involved anodic half‐reaction‐selective electrooxidation of 5‐hydroxymethylfurfural into 2,5‐furandicarboxylic acid (FDCA) on a hierarchically layered double hydroxide (CoFe@NiFe) with a cathodic HER in a two‐chamber system is reported. The overall reaction reaches 38 mA cm−2 at 1.40 V and exhibits 100% selectivity to yield FDCA and a nearly 100% Faraday efficiency with hydrogen production of 901 µmol cm−2. Several operando techniques confirm that the trivalent nickel species in the CoFe@NiFe catalyst are mainly responsible for this 100%‐selective oxidation reaction. This integrated overall reaction is thus a new strategy to utilize cheap catalysts and biomass derivatives to simultaneously produce value‐added chemicals and sustainable energy materials, and eventually to solve current challenges of energy depletion and environmental pollution.

The ongoing quest for understanding nonequilibrium dynamics of complex quantum systems underpins the foundation of statistical physics as well as the development of quantum technology. Quantum many-body scarring has recently opened a window into novel mechanisms for delaying the onset of thermalization, however its experimental realization remains limited to the Z2 state in a Rydberg atom system. Here we realize unconventional many-body scarring in a Bose-Hubbard quantum simulator with a previously unknown initial condition -the unit-filling state. Our measurements of entanglement entropy illustrate that scarring traps the many-body system in a low-entropy subspace. Further, we develop a quantum interference protocol to probe out-of-time correlations, and demonstrate the system's return to the vicinity of the initial state by measuring single-site fidelity. Our work makes the resource of scarring accessible to a broad class of ultracold-atom experiments, and it allows to explore its relation to constrained dynamics in lattice gauge theories, Hilbert space fragmentation, and disorder-free localization.

Aiming to solve the challenges of low detection accuracy, poor anti-interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning-based model, named You Only Look Once network v4 enhanced by EfficientNet and depthwise separable convolution (DSC; YOLOv4-ED), is proposed. In the YOLOv4-ED, EfficientNet is used as the backbone to improve the identification accuracy of indistinguishable defect targets in complex tunnel background and light conditions. Furthermore, DSC block is introduced to reduce the storage space of the model and thereby enhance the detection efficiency. The experimental results indicate that the mean average precision, F1 score, Model Size, and FPS of YOLOv4-ED are 81.84%, 81.99%, 49.3 MB, and 43.5 f/s, respectively, which is superior to the comparison models in both detection accuracy and efficiency. Based on robust and cost-effective YOLOv4-ED, a tunnel lining defect detection platform (TLDDP) with the capacity of automated inspection of various lining defects (i.e., water leakage, crack, rebar-exposed) is built. The established TLDDP can realize the high-precision and automatic detection of multiple tunnel lining defects under different lighting and complex background conditions of the practical in-service tunnel.