Search

Pauses, disfluencies and language problems in Alzheimer’s disease can be naturally modeled by fine-tuning Transformer-based pre-trained language models such as BERT and ERNIE. Using this method with pause-encoded transcripts, we achieved 89.6% accuracy on the test set of the ADReSS (Alzheimer’s Dementia Recognition through Spontaneous Speech) Challenge. The best accuracy was obtained with ERNIE, plus an encoding of pauses. Robustness is a challenge for large models and small training sets. Ensemble over many runs of BERT/ERNIE fine-tuning reduced variance and improved accuracy. We found that um was used much less frequently in Alzheimer’s speech, compared to uh. We discussed this interesting finding from linguistic and cognitive perspectives.

Fertigation technology is key to solve water pollution and inefficient fertilizer use. However, some early techniques cannot adapt to the current situation of labor shortages and large-scale planting. Therefore, it is necessary to consider farmers’ willingness to adopt more adaptive techniques. Specifically, we focus on whether early technology adoption will hinder technology renewal and whether the factors affecting the adoption of early and latest techniques are consistent. Through theoretical analysis and a survey, we find that farmers’ endowments such as income and labor force only affect the adoption intentions to the high-cost technique (Intelligent Irrigation Control System), but not early techniques (Venturi injector and Differential pressure tank), while farmers’ information processing ability and information acquisition channels affect both. Finally, the results of Propensity Score Matching show that early technology adoption will not become an obstacle to technology renewal.

Internet finance is a financial mode combining traditional financial industry with Internet technologies, which has become a crucial part of the financial field. Due to the rapid change of information technologies and public financial needs, Internet finance has produced quite a few specific operation modes, which have interested many scholars. To better appreciate its development process and innovation modes, we used bibliometrics to analyze 2,877 articles on Internet finance in Web of Science. Through the co-word network, co-citation network and various results generated by CiteSpace, we recognized six main modes of Internet finance, that is, Internet bank, peer to peer lending (P2P lending), crowdfunding, big data finance, digital currency and fintech. Emerging research topics and the development history of each mode are also detected. We find that the mainstream modes in current research are P2P lending and crowdfunding and the research on fintech and digital currency has just begun. Through the review, we also suggest some research directions for the research direction of each mode. These results will help to deepen relevant scholars’ understanding of Internet finance and provide guidance for them to choose research directions.