Seminar: Natural Language Processing

Natural language processing (NLP) deals with the computational analysis and snythesis of natural language text. In this seminar, we look at a subarea of NLP called computational sociolinguistics (CSL). CSL investigates research questions from the social sciences with empirical NLP technologies. Input text includes online news articles, social media posts, forum discussions, and similar. The focus is not only on the employed NLP technologies, but also on the insights into social phenomena and dynamics, raising a particular need for output interpretation and visualization. The aim of this seminar is to learn about basic ideas and recent research in CSL as well as to discuss the benefits and limitations of empirical text analysis on societal developments. 

Based on a few introductory talks, each participant will choose a sophisticated topic from recent related research. For this topic, a provided scientific paper has prepared and presented in a scientific talk, adding additional background knowledge where needed and possibly further literature. The talks are given in weekly sessions during the lecture time. In addition, the topic has to be summarized and discussed in detail in a 4-page paper-like article to be submitted in the middle of the lecture-free time.

• Basics of statistics
• Bachelor's course: Introduction to Natural Language Processing (not obligatory)

• Daniel Jurafsky and James H. Martin. 2009. Speech and Language Processing: An Introduction to Natural Language Processing, Speech Recognition, and Computational Linguistics. Prentice-Hall, 2nd edition. Free draft of third edition: Speech and Language Processing

• Organizational course information [slides]
• Part I – Introduction to Computational Sociolinguistics [slides]
• Part II – Overview of Seminar Topics [slides]