S
Sen Su
Researcher at Beijing University of Posts and Telecommunications
Publications - 206
Citations - 3803
Sen Su is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Computer science & Web service. The author has an hindex of 27, co-authored 187 publications receiving 3144 citations. Previous affiliations of Sen Su include Peking University.
Papers
More filters
Book ChapterDOI
Using case-based reasoning to support web service composition
TL;DR: The approach proposed by this paper can solve the problem of web service composition under the condition of insufficient and ill-defined knowledge, and can reduce the difficulty and cost ofweb service composition.
Journal ArticleDOI
Multi-Task Learning with Generative Adversarial Training for Multi-Passage Machine Reading Comprehension
Qiyu Ren,Xiang Cheng,Sen Su +2 more
TL;DR: MG-MRC is presented, a novel approach for multi-passage MRC via multi-task learning with generative adversarial training, which adopts the extract-then-select framework and proposes a hybrid method which combines boundary-based and content-based extracting methods to produce the answer candidate set and its representation.
Journal ArticleDOI
Identifying and tracking topic-level influencers in the microblog streams
TL;DR: A novel topic-level influence over time (TIT) model integrating the text, links and time to analyze the topic- level temporal influence of each user is proposed and an influence decay based approach to measure users’ topic- Level influence from the learned temporal influence is designed.
Journal ArticleDOI
A novel path-based approach for single-packet IP traceback
TL;DR: This approach makes use of the routing paths to set up traceback paths, instead of packet logging, so as to improve single-packet IP traceback in several dimensions.
Journal ArticleDOI
Reconciling Multiple Social Networks Effectively and Efficiently: An Embedding Approach
TL;DR: This paper proposes two frameworks, MASTER and MASTER+, that robustly and comprehensively reconcile multiple social networks, and designs an efficient Augmented Pre-Embedding model and Balance-aware Fuzzy Clustering algorithm for the high efficiency and the high accuracy.