Transfer learning and domain adaptive learning have been applied to various fields including computer vision (e.g., image recognition) and natural language processing (e.g., text classification). One of the benefits of transfer learning is to learn effectively and efficiently from limited labeled data with a pretrained model. In the shared task of identifying and categorizing offensive language in social media, we preprocess the dataset according to the language behaviors on social media, and then adapt and fine-tune the Bidirectional Encoder Representation from Transformer (BERT) pre-trained by Google AI Language team 1. Our team NULI wins the first place (1st) in Sub-task A-Offensive Language Identification and is ranked 4th and 18th in Sub-task B-Automatic Categorization of Offense Types and Sub-task C-Offense Target Identification respectively.

No abstract

No abstract

This paper analyzes the e¤ects of buyer and seller risk aversion in …rst and secondprice auctions. The setting is the classic one of symmetric and independent private values, with ex ante homogeneous bidders. However, the seller is able to optimally set the reserve price. In both auctions the seller's optimal reserve price is shown to decrease in his own risk aversion, and more so in the …rst-price auction. Thus, greater seller risk aversion increases the ex post e¢ ciency of both auctions, and especially that of the …rst-price auction. The seller's optimal reserve price in the …rst-price, but not in the second-price, auction decreases in the buyers'risk aversion.Thus, greater buyer risk aversion also increases the ex post e¢ ciency of the …rst but not the second-price auction. At the interim stage, the …rst-price auction is preferred by all buyer types in a lower interval, as well as by the seller.

BackgroundDynamic protein phosphorylation is an essential regulatory mechanism in various organisms. In this capacity, it is involved in a multitude of signal transduction pathways. Kinase-specific phosphorylation data lay the foundation for reconstruction of signal transduction networks. For this reason, precise annotation of phosphorylated proteins is the first step toward simulating cell signaling pathways. However, the vast majority of kinase-specific phosphorylation data remain undiscovered and existing experimental methods and computational phosphorylation site (P-site) prediction tools have various limitations with respect to addressing this problem.ResultsTo address this issue, a novel protein kinase identification web server, PKIS, is here presented for the identification of the protein kinases responsible for experimentally verified P-sites at high specificity, which incorporates the composition of monomer spectrum (CMS) encoding strategy and support vector machines (SVMs). Compared to widely used P-site prediction tools including KinasePhos 2.0, Musite, and GPS2.1, PKIS largely outperformed these tools in identifying protein kinases associated with known P-sites. In addition, PKIS was used on all the P-sites in Phospho.ELM that currently lack kinase information. It successfully identified 14 potential SYK substrates with 36 known P-sites. Further literature search showed that 5 of them were indeed phosphorylated by SYK. Finally, an enrichment analysis was performed and 6 significant SYK-related signal pathways were identified.ConclusionsIn general, PKIS can identify protein kinases for experimental phosphorylation sites efficiently. It is a valuable bioinformatics tool suitable for the study of protein phosphorylation. The PKIS web server is freely available at http://bioinformatics.ustc.edu.cn/pkis.