XLIM-PHOT
Abstract:Nanoparticle Tracking Analysis (NTA) provides a simple method to determine individual nanoparticle size. However, because size quantification is based on the slowly converging statistical law of random event, its intrinsic error is large, especially in case of limited event number, e.g. for weak scattering nanoparticles. Here, we introduce an NTA improvement by analyzing each individual NP trajectory while taking into account the other trajectories with a weighting coefficient. This weighting coefficient is directly derived from the optical signature of each particle measured by quantitative phase microscopy. The simulations and experimental results demonstrate the improvement of NTA accuracy, not only for mono-disperse but also for poly-disperse particle solutions.
Abstract:In this paper, we introduce our approaches using Transformer-based models for different problems of the COLIEE 2021 automatic legal text processing competition. Automated processing of legal documents is a challenging task because of the characteristics of legal documents as well as the limitation of the amount of data. With our detailed experiments, we found that Transformer-based pretrained language models can perform well with automated legal text processing problems with appropriate approaches. We describe in detail the processing steps for each task such as problem formulation, data processing and augmentation, pretraining, finetuning. In addition, we introduce to the community two pretrained models that take advantage of parallel translations in legal domain, NFSP and NMSP. In which, NFSP achieves the state-of-the-art result in Task 5 of the competition. Although the paper focuses on technical reporting, the novelty of its approaches can also be an useful reference in automated legal document processing using Transformer-based models.