Results 101 to 110 of about 2,466 (175)

Faith and Fate: Limits of Transformers on Compositionality

, 2023
Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneously show failures on surprisingly trivial problems.
Bhagavatula, Chandra, Bras, Ronan Le, Choi, Yejin, Dziri, Nouha, Ettinger, Allyson, Harchaoui, Zaid, Hwang, Jena D., Jian, Liwei, Li, Xiang Lorraine, Lin, Bill Yuchen, Lu, Ximing, Ren, Xiang, Sanyal, Soumya, Sclar, Melanie, Welleck, Sean, West, Peter   +15 more
core  

Text Style Transfer Evaluation Using Large Language Models

, 2023
Evaluating Text Style Transfer (TST) is a complex task due to its multifaceted nature. The quality of the generated text is measured based on challenging factors, such as style transfer accuracy, content preservation, and overall fluency.
Fellenz, Sophie, Kloft, Marius, Nagda, Mayank, Ostheimer, Phil   +3 more
core  

Methods and Evaluation of AI-Based Meteorological Models for Zenith Tropospheric Delay Prediction

Remote Sensing
Zenith Tropospheric Delay (ZTD) is a significant error source affecting the accuracy of certain space geodetic measurements. This study evaluates the performance of Artificial Intelligence (AI) based meteorological models, such as Fengwu and Pangu, in ...
Si Xiong, Jiamu Mei, Xinchuang Xu, Ziyu Shen, Liangke Huang   +4 more
doaj   +1 more source

Italian Crossword Generator: An In-depth Linguistic Analysis in Educational Word Puzzles

IJCoL
Educational crosswords offer numerous benefits for students, including increased engagement, improved understanding, critical thinking, and memory retention.
Kamyar Zeinalipour, Tommaso Iaquinta, Asya Zanollo, Giovanni Angelini, Leonardo Rigutini, Marco Maggini, Marco Gori   +6 more
doaj  

Evaluation of Tropospheric Delays over China from the High-Resolution Pangu-Weather Model at Multiple Forecast Scales

Remote Sensing
Tropospheric delay is recognized as one of the main error sources affecting Global Navigation Satellite System (GNSS) positioning accuracy. Previous studies have only employed artificial intelligence-based weather models with low temporal resolution for ...
Shuangping Li, Bin Zhang, Haohang Bi, Liangke Huang, Bo Shi, Qingsong Ai   +5 more
doaj   +1 more source

FastPersist: Accelerating Model Checkpointing in Deep Learning

Model checkpoints are critical Deep Learning (DL) artifacts that enable fault tolerance for training and downstream applications, such as inference. However, writing checkpoints to persistent storage, and other I/O aspects of DL training, are mostly ...
He, Yuxiong, Ruwase, Olatunji, Wang, Guanhua, Xie, Bing   +3 more
core  

How Can Generative AI Empower Domain Experts in Creating Process Models? [PDF]

Considering the human factor in information systems is a key to future digitalization efforts, as stated in the Industry5.0 research and innovation actions of the EU.
Benzin, Janik-Vasily, Kampik, Timotheus, Klievtsova, Nataliia, Mangler, Juergen, Rinderle-Ma, Stefanie   +4 more
core   +1 more source

An optimized BP neural network for modeling zenith tropospheric delay in the Chinese mainland using coupled particle swarm and genetic algorithm

Geo-spatial Information Science
Tropospheric delay influences high-precision navigation positioning and precipitable water vapor retrieval with the Global Navigation Satellite System (GNSS).
Liangke Huang, Haohang Bi, Hongxing Zhang, Shitai Wang, Fasheng Liao, Lilong Liu, Weiping Jiang   +6 more
doaj   +1 more source

A New Empirical Model of Weighted Mean Temperature Combining ERA5 Reanalysis Data, Radiosonde Data, and TanDEM-X 90m Products over China

Remote Sensing
Weighted mean temperature (Tm) is an important parameter in the water vapor inversion of global navigation satellite systems (GNSS). High-precision Tm values can effectively improve the accuracy of GNSS precipitable water vapor.
Jingkui Zhang, Liu Yang, Jian Wang, Yifan Wang, Xitian Liu   +4 more
doaj   +1 more source

Investigating antiquities trafficking with generative pre-trained transformer (GPT)-3 enabled knowledge graphs: A case study. [PDF]

Open Res Eur, 2023
Graham S, Yates D, El-Roby A.
europepmc   +1 more source