No abstract

No abstract

Commenting systems play increasingly important roles in the interactive web applications. Meanwhile, more and more web applications are visited on mobile devices. However, the intermittent connection of mobile networks and resource limitation of mobile devices pose great challenges, mainly in terms of interactive responsiveness and data consistency. In this paper, we present the first work of partial replication solution based on collaborative editing techniques, which can address the issues of local responsiveness and resource limitation on mobile commenting systems. We report how we address the consistency maintenance challenges that come with the partial replication approach. With this approach, users are allowed to smoothly comment anywhere anytime. The comment thread can be incrementally updated and automatically synchronized with strong data consistency guarantees. We implemented a system prototype called Hydra and evaluated it on a real data set.

No abstract

Understanding protein sequences is vital and urgent for biology, healthcare, and medicine. Labeling approaches are expensive yet time-consuming, while the amount of unlabeled data is increasing quite faster than that of the labeled data due to low-cost, high-throughput sequencing methods. In order to extract knowledge from these unlabeled data, representation learning is of significant value for protein-related tasks and has great potential for helping us learn more about protein functions and structures. The key problem in the protein sequence representation learning is to capture the co-evolutionary information reflected by the interresidue co-variation in the sequences. Instead of leveraging multiple sequence alignment as is usually done, we propose a novel method to capture this information directly by pre-training via a dedicated language model, i.e., Pairwise Masked Language Model (PMLM). In a conventional masked language model, the masked tokens (i.e. amino acid residues) are modeled by conditioning on the unmasked tokens only, but processed independently to each other. However, our proposed PMLM takes the dependency among masked tokens into consideration, i.e., the probability of a token pair is not equal to the product of the probability of the two tokens. By applying this model, the pre-trained encoder is able to generate a better representation for protein sequences. Our result shows that the proposed method can effectively capture the inter-residue correlations and improves the performance of contact prediction by up to 9% compared to the MLM baseline under the same setting. The proposed model also significantly outperforms the MSA baseline by more than 7% on the TAPE contact prediction benchmark when pretrained on a subset of the sequence database which the MSA is generated from, revealing the potential of the sequence pre-training method to surpass MSA based methods in general.