Papers by Simon Rodier
Online Near-Duplicate Detection of News Articles (2020.lrec-1)
Copied to clipboard
| Challenge: | Near-duplicate documents are prevalent in news corpora and cost significant . bloating corporata with redundant information and computational costs are among the costs . |
| Approach: | They propose an online system which flags a near-duplicate document by finding its most likely original. |
| Outcome: | The proposed system can be used in many real-world applications. |