The effective of information retrieval (IR) systems have become more important than ever. Deep IR models have gained increasing attention for its ability to automatically learning features from raw text;thus, many dee...
详细信息
Representing texts as fixed-length vectors is central to many language processing tasks. Most traditional methods build text representations based on the simple Bag-of-Words (BoW) representation, which loses the rich ...
详细信息
In recent years, deep neural models have been widely adopted for text matching tasks, such as question answering and information retrieval, showing improved performance as compared with previous methods. In this paper...
详细信息
Entity alignment aims to identify semantical matchings between entities from different groups. Traditional methods (e.g., attribute comparison based methods, clustering based methods, and active learning methods) are ...
详细信息
ISBN:
(纸本)9781538631218
Entity alignment aims to identify semantical matchings between entities from different groups. Traditional methods (e.g., attribute comparison based methods, clustering based methods, and active learning methods) are usually supervised by labelled data as prior knowledge. Since it is not trivial to label data for training, researchers have recently turned to unsupervised methods, and have thus developed similarity based methods, probabilistic methods, hierarchical graph model based methods, etc. As an important part of a knowledge graph, entities contain rich semantical information that can be well learned by knowledge graph embedding in a low-dimensional vector space. However, existing methods for entity alignment have paid little attention to knowledge graph embedding. In this paper, we propose a Self-learning and Embedding based method for Entity Alignment, thus called SEEA, to iteratively find semantically matched entity pairs, which makes full use of semantical information contained in the attributes of entities. Experiments on two realistic datasets and comparison with the baselines validate the effectiveness and merits of the proposed method.
A 2.1 year periodic oscillation of the γ-ray flux from the blazar PG 1553+113 has previously been tentatively identified in ∼ 7 years of data from the Fermi Large Area Telescope. After 15 years of Fermi sky-survey o...
详细信息
The first Better evidence and RecommendatIons for the next Generation HealTh—BRIGHT symposium was held in Chongqing, China between June 21 and 23, 2024. The symposium did not only showcase the recent progress made by...
详细信息
The first Better evidence and RecommendatIons for the next Generation HealTh—BRIGHT symposium was held in Chongqing, China between June 21 and 23, 2024. The symposium did not only showcase the recent progress made by multidisciplinary teams in generating and translating evidence for children's healthcare, guideline development and evaluation, and the utilization of AI applications in pediatrics but also fostered transnational and transregional cooperation to promote the advancement of high-quality evidence and guidelines in this field. The symposium contributed significantly to the future development and transformation of research endeavors in pediatrics.
Influence maximization is the problem of selecting k nodes in a social network to maximize their influence spread. The problem has been extensively studied but most works focus on the submodular influence diffusion mo...
ISBN:
(纸本)9781510860964
Influence maximization is the problem of selecting k nodes in a social network to maximize their influence spread. The problem has been extensively studied but most works focus on the submodular influence diffusion models. In this paper, motivated by empirical evidences, we explore influence maximization in the non-submodular regime. In particular, we study the general threshold model in which a fraction of nodes have non-submodular threshold functions, but their threshold functions are closely upper- and lower-bounded by some submodular functions (we call them ε-almost submodular). We first show a strong hardness result: there is no l/nγ/c approximation for influence maximization (unless P = NP) for all networks with up to nγ ε-almost submodular nodes, where γ is in (0,1) and c is a parameter depending on ε. This indicates that influence maximization is still hard to approximate even though threshold functions are close to submodular. We then provide (l - ε)ℓ(1 - 1/ε) approximation algorithms when the number of ε-almost submodular nodes is ℓ. Finally, we conduct experiments on a number of real-world datasets, and the results demonstrate that our approximation algorithms outperform other baseline algorithms.
As online fraudsters invest more resources, including purchasing large pools of fake user accounts and dedicated IPs, fraudulent attacks become less obvious and their detection becomes increasingly challenging. Existi...
详细信息
We are now witnessing the increasing availability of event stream data, i.e., a sequence of events with each event typically being denoted by the time it occurs and its mark information (e.g., event type). A fundament...
详细信息
We develop efficient numerical integration methods for computing an integral whose integrand is a product of a smooth function and the Gaussian function with a small standard deviation. Traditional numerical integrati...
详细信息
暂无评论