CNN-Based Novelty Detection with Effectively Incorporating Document-Level Information


KIPS Transactions on Computer and Communication Systems, Vol. 9, No. 10, pp. 231-238, Oct. 2020
https://doi.org/10.3745/KTCCS.2020.9.10.231,   PDF Download:
Keywords: Deep Learning, CNN, Novelty Detection
Abstract

With a large number of documents appearing on the web, document-level novelty detection has become important since it can reduce the efforts of finding novel documents by discarding documents sharing redundant information already seen. A recent work proposed a convolutional neural network (CNN)-based novelty detection model with significant performance improvements. We observed that it has a restriction of using document-level information in determining novelty but assumed that the document-level information is more important. As a solution, this paper proposed two methods of effectively incorporating document-level information using a CNN-based novelty detection model. Our methods focus on constructing a feature vector of a target document to be classified by extracting relative information between the target document and source documents given as evidence. A series of experiments showed the superiority of our methods on a standard benchmark collection, TAP-DLND 1.0.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. Jo, H. Oh, S. Im and S. Kim, "CNN-Based Novelty Detection with Effectively Incorporating Document-Level Information," KIPS Transactions on Computer and Communication Systems, vol. 9, no. 10, pp. 231-238, 2020. DOI: https://doi.org/10.3745/KTCCS.2020.9.10.231.

[ACM Style]
Seongung Jo, Heung-Seon Oh, Sanghun Im, and Seonho Kim. 2020. CNN-Based Novelty Detection with Effectively Incorporating Document-Level Information. KIPS Transactions on Computer and Communication Systems, 9, 10, (2020), 231-238. DOI: https://doi.org/10.3745/KTCCS.2020.9.10.231.