Natural Language Processing (NLP), i.e. enabling computers to derive meaning from and interact with human language, is a crucial building block of numerous research fields in computer and information science such as:
- Information Retrieval (IR)
- Question Answering
- Plagiarism Detection
- Information Extraction (IE)
- Named Entity Recognition
- Co-Reference Resolution
- Relationship Extraction
- Computational Linguistics
- Part-of-Speech Tagging
- Sentence Breaking
- Word Sense Disambiguation
- Natural Language Understanding
- Morphological Segmentation
- Machine Translation
- Text Mining
- Topic Detection
- Automatic Summarization
- Sentiment Analysis
- Discourse Analysis
- Text Simplification
- Optical Character Recognition
- Speech Processing
- Speech Recognition
- Natural Language Generation
In this seminar, participants will survey and apply state-of-the-art NLP methods to solve real-world problems.
Introductory literature (independent research of topic-specific literature is required):
- S. Bird, E. Klein, and E. Loper. Natural Language Processing with Python. O’Reilly Media, Inc., 1st edition, 2009. ISBN 0596516495, 9780596516499. KonSearch: http://goo.gl/SVHV3s, free online version (1st edition): www.nltk.org/book_1ed/, (2nd edition):www.nltk.org/book_2ed/
- D. Jurafsky and J. H. Martin. Speech and Language Processing (2nd Edition) (Prentice Hall Series in Artificial Intelligence). Prentice Hall, 2 edition, 2008. ISBN 0131873210. KonSearch:http://goo.gl/eP9ReG
- C. D. Manning and H. Schütze. Foundations of Statistical Natural Language Processing. The MIT Press, 6 edition, 2003. KonSearch:http://goo.gl/uaYsQT
- C. D. Manning, P. Raghavan, and H. Schütze. An Introduction to Information Retrieval. Cambridge University Press, Cambridge, England, online edition, 2008. KonSearch: http://goo.gl/ZMAixm , free online version:http://nlp.stanford.edu/IR-book/
The seminar can serve as a starting point for a topically related bachelor's or master's project and thesis. For current project and theses proposals visit:http://www.isg.uni-konstanz.de/students-corner/
For the theoretical research project:
- presentation (30 min)
- term paper (8-10 pages per person, ACM style)
For the practical research project:
- Developed application
- Presentation (30 min)
- Developer documentation (min 3 pages per person, ACM style)
Group work is possible for both projects.
Seminar participants can choose to complete either a theoretical or a practical research project as part of the seminar.
For the theoretical research project, participants will pick a topic related to NLP research and applications according to their own interests or from a pool of suggestions that will be provided. For their topic, the participants will give an overview of the state-of-the-art relevant to the topic in a presentation during the seminar (30 min) and a term paper (8 - 10 pages per person, ACM style) due at the end of the seminar. The theoretical research project is best suited to compile a state-of-the-art review in preparation of a subsequent practical BA/MA project and/or thesis in the same area.
For the practical research project, participants will use NLP methods to implement a system that solves a real-world application problem. Participants can suggest a problem or choose from a number of suggestions that will be provided. Aside from the working application, completing the seminar requires a giving a presentation (30 min) on the project and a compiling a developer documentation for the application (min 3 pages ACM style per person).
Seminar participants will gain an overview of state-of-the-art NLP methods. They will be able to describe the current trends and challenges in NLP research and applications, as well as the predominant approaches for tackling these challenges.
For the theoretical research project, each participant will perform an in-depth literature review on one current NLP approach. The participants will present their findings in an academic paper and a 30 minute long presentation during one of the seminar sessions. Through this process, which the lecturers supervise and guide, the participants will train their ability to:
- find, organize, and systematically read relevant research papers
- analyze, compare, and contrast research approaches and findings
- structure, write, and format an academic paper
- present their work using appropriate presentation techniques and presentation aids
- answer questions and discuss their work with peers
For the practical research project, participants will pick a real-world application problem that can be solved using NLP technology. The participants will design and implement an application that addresses the identified problem. By completing this task, participants will gain hands-on experience in NLP application development.
By successfully completing the theoretical or practical research project, participants will achieve valuable preparation in terms of the knowledge and methodological skills required to successfully complete a subsequent bachelor’s or master’s project.
Total workload: 4 ECTS = 120 hours