We have completed the first edition of the Text Analysis and Retrieval course, which combines natural language processing, information retrieval, and relevant machine learning techniques. The most fulfilling part of the course were the student projects in which the majority of the student groups successfully tackled a real-world NLP or IR problem.
Everyone should teach what they are best in. For us at TakeLab that is natural language processing and information retrieval. For the first time this year, we prepared a course bringing to students a wide-range of topics in NLP and IR. The course aimed to provide our students with an understanding of the theoretical foundations and applications of text analysis and retrieval methods, as well as best practices, trends, and challenges in these exciting and growing fields.
We gave an overview of both traditional and advanced methods for text analysis and retrieval. The first part of the course dealt with the basic natural language processing tasks, document representation and retrieval, as well as document classification and clustering. The second part dealt with information extraction and text mining, with an extra emphasis on hot topics in the NLP community, such as semantic text similarity and sentiment analysis.
We believe that the students who passed the course gained a working familiarity with basic natural language processing methods and an understanding of the main information retrieval and information extraction models, as well as their theoretical foundations, advantages, and limitations.
A very important part of the coursework was a group project, in which our students designed, implemented, and evaluated a solution for a real-world document retrieval or text analysis problem.
Want to see how they did? Take a peek at their project reports here: Text Analyis and Retrieval 2014 – Course Project Reports