Chemical-induced disease (CID) relation extraction from biomedical articles plays an important role in disease treatment and drug development. Existing methods are insufficient for capturing complete document level semantic information due to ignoring semantic information of entities in different sentences. In this work, we proposed an effective document-level relation extraction model to automatically extract intra-/inter-sentential CID relations from articles. Firstly, our model employed BERT to generate contextual semantic representations of the title, abstract and shortest dependency paths (SDPs). Secondly, to enhance the semantic representation of the whole document, cross attention with self-attention (named cross2self-attention) between abstract, title and SDPs was proposed to learn the mutual semantic information. Thirdly, to distinguish the importance of the target entity in different sentences, the Gaussian probability distribution was utilized to compute the weights of the co-occurrence sentence and its adjacent entity sentences. More complete semantic information of the target entity is collected from all entities occurring in the document via our presented document-level R-BERT (DocR-BERT). Finally, the related representations were concatenated and fed into the softmax function to extract CIDs. We evaluated the model on the CDR corpus provided by BioCreative V. The proposed model without external resources is superior in performance as compared with other state-of-the-art models (our model achieves 53.5%, 70%, and 63.7% of the F1-score on inter-/intra-sentential and overall CDR dataset). The experimental results indicate that cross2self-attention, the Gaussian probability distribution and DocR-BERT can effectively improve the CID extraction performance. Furthermore, the mutual semantic information learned by the cross self-attention from abstract towards title can significantly influence the extraction performance of document-level biomedical relation extraction tasks.

Knowledge graphs are collections of factual triples. Link prediction aims to predict lost factual triples in knowledge graphs. In this paper, we present a novel capsule network method for link prediction taking advantages of quaternion. More specifically, we explore two methods, including a relational rotation model called QuaR and a deep capsule neural model called CapS-QuaR to encode semantics of factual triples. QuaR model defines each relation as a rotation from the head entity to the tail entity in the hyper-complex vector space, which could be used to infer and model diverse relation patterns, including: symmetry/anti-symmetry, reversal and combination. Based on these characteristics of quaternions, we use the embeddings of entities and relations trained from QuaR as the input to CapS-QuaR model. Experimental results on multiple benchmark knowledge graphs show that the proposed method is not only scalable, but also able to predict the correctness of triples in knowledge graphs and significantly outperform the existing state-of-the-art models for link prediction. Finally, the evaluation of a real dataset for search personalization task is conducted to prove the effectiveness of our model.

This paper presents a novel High Efficiency Video Coding (HEVC) based screen content coding scheme providing lossy-to-lossless compression support. The paper follows a two-layer design approach which allows for backward compatibility with the conventional HEVC standard for the base-layer and yields lossless compression when decoding the enhancement-layer. The system employs Golomb based binarization and context-based arithmetic coding to efficiently encode the enhancement-layer. Performance evaluations using 4:4:4 screen content sequences are carried out. The results show that the proposed system substantially outperforms lossless intra- HEVC and single-layer JPEG-LS.

For the ship pipe routing design (SPRD) problem, previous studies have mainly employed bio-inspired algorithms such as multi-objective ant colony optimization (MOACO), non-dominated sorting genetic algorithm II (NSGA-II), and multi-objective particle swarm optimization (MOPSO). This paper proposes a novel approach based on the multi-objective A* (MOA*) algorithm to solve the SPRD. First, the optimization objectives and constraints of the SPRD problem are defined, and then an MOA*-based routing framework is developed. The time and space complexities of the approach are analyzed, and key components such as the cost functions, the solution dominance relationship, dynamic probability-based pruning, and neighbor node exploration strategy are designed to enhance solution diversity and search efficiency. Additionally, a space cascade expansion method is proposed to improve the computational efficiency of the MOA* in large-scale grid spaces. Comparative studies with MOACO, NSGA-II, GA-A*, and gray wolf optimization (GWO) on simulated cases of varying complexities and practical piping scenarios demonstrate the effectiveness of the MOA*. Furthermore, the applicability of the MOA* is validated against practical piping requirements, including the rapid generation of sub-optimal solutions, non-orthogonal routing, and partitioned pipe layouts. Experimental results, supported by a C++/OpenGL-based prototype software, show that the MOA* requires no extensive parameter tuning, exhibits stable computational efficiency and optimization capability, and demonstrates competitive performance in Pareto-optimal diversity compared with other algorithms.