This module falls under the heading "Enterprise Information Search and Management".
Knowledge intensive companies produce each year a large amount of documents that store the outcomes of their knowledge production. In order to make them accessible and useful for employees but also customers, companies need to have efficient ways of processing and indexing these documents to support at least the information search and retrieval. The techniques ranging from indexing at the word level through fuzzy matches to more advanced entity and graph based methods are used to understand and index the content in the documents. This course will provide insights into those methods and will supplement them with examples of tools and algorithms.
Specific topics covered in this course are:
- Word based indexing and processing of documents
- Fuzzy based processing and indexing of documents
- Entity and graph based approaches for processing and indexing of documents
- Clustering and Classification of Documents