Learning Relational Fractals for Deep Knowledge Graph Embedding in Online Social Networks

Ji, Zhang; Tan, Leonard; Tao, Xiaohui; Wang, Dianwei; Ying, Josh Jia-Ching; Wang, Xin

doi:10.1007/978-3-030-34223-4_42

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, graph representation-based strategies show their excited performance in expressing information in complex condition, such as social network representation [3,[7][8][9][10], chemical molecule representation [11][12][13][14][15] and so forth. Because of the characteristics of real-world data and the properties of graphs which can handle much more complex information, we intend to harness the wisdom of graphs to represent the semantic information in sentences.…”

Section: Introductionmentioning

confidence: 99%

From text to graph: a general transition-based AMR parsing using neural network

Luo

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

Semantic understanding is an essential research issue for many applications, such as social network analysis, collective intelligence and content computing, which tells the inner meaning of language form. Recently, Abstract Meaning Representation (AMR) is attracted by many researchers for its semantic representation ability on an entire sentence. However, due to the non-projectivity and reentrancy properties of AMR graphs, they lose some important semantic information in parsing from sentences. In this paper, we propose a general AMR parsing model which utilizes a two-stack-based transition algorithm for both Chinese and English datasets. It can incrementally parse sentences to AMR graphs in linear time. Experimental results demonstrate that it is superior in recovering reentrancy and handling arcs while is competitive with other transition-based neural network models on both English and Chinese datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

From text to graph: a general transition-based AMR parsing using neural network

Luo

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Using online social networks has appeared to be not only a way of communication but also a lifestyle. Consequently, Web social media has attracted much interest from the research community, aiming at gaining a better understanding of not only individual users' but also their collective behaviours, resulting in many theoretical and methodological advancements such as online social network analysis (e.g., [2]), public opinions (e.g., [3]), and community's health and wellbeing on social networks (e.g., [1]). The opportunity has become more apparent and significant, along with the large volume of online social media data becoming available day-by-day.…”

mentioning

confidence: 99%