Name
Abstract | ||
|---|---|---|
What are the most representative research topics in Artificial Intelligence (AI)? We formulate the problem as extracting top-k topics that can best represent a given area with the help of knowledge base. We theoretically prove that the problem is NP-hard and propose an optimization model, FastKATE, to address this problem by combining both explicit and latent representations for each topic. We leverage a large-scale knowledge base (Wikipedia) to generate topic embeddings using neural networks and use this kind of representations to help capture the representativeness of topics for given areas. We develop a fast heuristic algorithm to efficiently solve the problem with a provable error bound. We evaluate the proposed model on three real-world datasets. Experimental results demonstrate our model's effectiveness, robustness, real-timeness (return results in <;1s), and its superiority over several alternative methods. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/DSC.2018.00016 | 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC) |
Keywords | DocType | Volume |
knowledge discovery,data mining,topic extraction,knowledge base,heuristic search | Conference | abs/1710.04822 |
ISBN | Citations | PageRank |
978-1-5386-4211-5 | 1 | 0.36 |
References | Authors | |
8 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fang Zhang | 1 | 48 | 14.46 |
| Xiaochen Wang | 2 | 18 | 9.25 |
| Jingfei Han | 3 | 1 | 0.36 |
| Jie Tang | 4 | 5871 | 300.22 |
| Shiyin Wang | 5 | 4 | 0.75 |