We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Using a Topic Based Model to Automate Indexing and Routing of Incoming Enterprise Documents.
- Authors
RĀTS, Juris; PEDE, Inguna
- Abstract
A machine learning based model aimed at automation of the indexing and routing of the incoming documents of the enterprise is proposed in this article. An overall automation process as well as support for trainset annotation and a model for handling of streams of incoming documents is described. Experts are supported during the annotation process by grouping the stream of documents into clusters of similar documents. It is expected that this may improve both the process of topic selection and that of document annotation. A binary classification-based model for topic prediction is proposed and analysed. Classification bots are trained for each of the largest topics and executed on incoming documents afterward. A number of model parameters are described and analysed.
- Subjects
DOCUMENT clustering; GROUP process; CLASSIFICATION; INDEXING; BUSINESS enterprises; AUTOMATION
- Publication
Baltic Journal of Modern Computing, 2022, Vol 10, Issue 3, p545
- ISSN
2255-8942
- Publication type
Article
- DOI
10.22364/bjmc.2022.10.3.25