A New Approach for Topic Detection using Adaptive Neural Networks
This work addresses topic detection for processing electronic information, but it appears incremental as it combines existing methods without clear SOTA gains.
The paper tackles topic detection by proposing ClusART, a three-phase approach combining FuzzyART and Paragraph Vector, and reports that on the 20 Newsgroups dataset, it detects almost relevant topics.
Topic detection becomes more important due to the increase of information electronically available and the necessity to process and filter it. In this context our master's thesis work was carried out, where we proposed to present a new approach to the detection of topics called ClusART. Thus, we proposed a three-phase approach, namely : a first phase during which lexical preprocessing was conducted. A second phase during which the construction and generation of vectors representing the documents was carried out. A third phase which is itself composed of two steps. In the first step we used the FuzzyART algorithm for the training phase. In the second step we used a classifier using Paragraph Vector for the test phase. The comparative study of our approach on the 20 Newsgroups dataset showed that our approach is able to detect almost relevant topics.