-
Chapter and Conference Paper
BoundEst: Estimating Join Cardinalities with Tight Upper Bounds
Cardinality estimation is a critical component of query optimization. Despite extensive research, achieving efficient and accurate estimation for join queries remains challenging. Estimating tight upper bounds...
-
Article
2SCE-4SL: a 2-stage causality extraction framework for scientific literature
Extracting causality from scientific literature is a crucial task that underpins many downstream knowledge-driven applications. To this end, this paper presents a novel causality extraction framework for scien...
-
Article
COVID-19: a disruptive impact on the knowledge support of references
According to existing research, in the general scientific backdrop, individuals prefer to employ old and well-established knowledge to promote scientific advancement, resulting in the progress of science in a ...
-
Article
Heterogeneous data fusion and loss function design for tooth point cloud segmentation
Tooth point cloud segmentation plays an important role in the digital dentistry, and has received much attention in the past decade. Recently, methods based on the graph neural network have made significant pr...
-
Chapter and Conference Paper
Research on Optimization of Fuzzing Test of Unknown Protocol Based on Message Type
In recent years, due to the large number of unknown protocols, it is necessary to study the security of unknown protocols. IFuzzing is a universal method that can be used to study unknown protocols. In unknown...
-
Chapter and Conference Paper
State Machine Inference Method of Unknown Binary Protocol Based on Recurrent Neural Network
The state machine of binary protocol can effectively reflect the behavior characteristics of the protocol, and its inference results are often not highly influenced by the protocol format information and logic...
-
Chapter and Conference Paper
Causal Discovery and Knowledge Linkage in Scientific Literature: A Case Study in Biomedicine
[Motivation] Scientific literature is the main carrier to express innovation thinking, and the discovery of laws of knowledge from the literature is the necessary basis for scientific research to achieve innov...
-
Article
Fault-tolerant routing algorithm based on disjoint paths in 3-ary n-cube networks with structure faults
The 3-ary n-cube network is widely used in large-scale multi-processor parallel computers. It is an important issue to design high-performance communication technology with fault tolerance. In this paper, we stud...
-
Article
Deep bi-directional interaction network for sentence matching
The goal of sentence matching is to determine the semantic relation between two sentences, which is the basis of many downstream tasks in natural language processing, such as question answering and information...
-
Article
Communication and performance evaluation of 3-ary n-cubes onto network-on-chips
-
Article
Fault-tolerant hamiltonian cycles and paths embedding into locally exchanged twisted cubes
The foundation of information society is computer interconnection network, and the key of information exchange is communication algorithm. Finding interconnection networks with simple routing algorithm and hig...
-
Chapter and Conference Paper
Improving Entity Linking by Encoding Type Information into Entity Embeddings
Entity Linking (EL) refers to the task of linking entity mentions in the text to the correct entities in the Knowledge Base (KB) in which entity embeddings play a vital and challenging role because of the subt...
-
Chapter and Conference Paper
Using Feed-Forward Network for Fast Arbitrary Style Transfer with Contextual Loss
Image style transfer is a method that extracts its style from the style image and applies this style to content image. Since the introduction of neural style transfer, the field of style transfer has developed...
-
Chapter and Conference Paper
LRRA:A Transparent Neural-Symbolic Reasoning Framework for Real-World Visual Question Answering
The predominant approach of visual question answering (VQA) relies on encoding the image and question with a “black box" neural encoder and decoding a single token into answers such as “yes” or “no”. Despite t...
-
Chapter and Conference Paper
Enhancing Underwater Image Using Multi-scale Generative Adversarial Networks
Wavelength-dependent light absorption and scattering will reduce the quality of underwater images. Therefore, the characteristics of underwater images are different from those taken in natural. Low-quality und...
-
Chapter and Conference Paper
Improving Low-Resource Named Entity Recognition via Label-Aware Data Augmentation and Curriculum Denoising
Deep neural networks have achieved state-of-the-art performances on named entity recognition (NER) with sufficient training data, while they perform poorly in low-resource scenarios due to data scarcity. To so...
-
Chapter and Conference Paper
Construction of Completely Independent Spanning Tree Based on Vertex Degree
Interconnection networks have been extensively studied in the field of parallel computer systems. In the interconnection network, completely independent spanning tree (CISTs) plays an important role in the rel...
-
Chapter and Conference Paper
Explore Coarse-Grained Structures for Syntactically Controllable Paraphrase Generation
Syntactically controlled paraphrase generation can produce diverse paraphrases by exposing syntactic control, where both semantic preservation and syntactic variations are two important factors. Previous works...
-
Chapter and Conference Paper
A Joint Model for Graph-Based Chinese Dependency Parsing
In Chinese dependency parsing, the joint model of word segmentation, POS tagging and dependency parsing has become the mainstream framework because it can eliminate error propagation and share knowledge, where...
-
Article
Context-aware user preferences prediction on location-based social networks
Recently, the increasing number of mobile users in location-based social networks (LBSNs) has generated large amounts of data, which provides unprecedented opportunities to study mobile user preferences for lo...