Natural Language Processing (NLP)

The Natural Language Processing (NLP) group develops methods, algorithms, and tools for the automatic analysis of natural language. The group focuses on questions related to processing, understanding and generating discourse. It works on coreference resolution with a particular focus on appropriate representations for the task. It develops models of local coherence, most recently an unsupervised, graph-based version of the entity grid with applications in text generation, assessing readability and automatic summarization. The group is also interested in word sense disambiguation and its relations to discourse processing.


PhD. Thesis Defended

Angela Fahrni (second from the right, with her examination committee) has successfully defended her PhD. thesis on “Joint Discourse-aware Concept Disambiguation and Clustering”. Angela is a former HITS doctoral student and has been working as a PostDoc at IBM Research in Zurich since submitting her thesis in October 2014.

Author Disambiguation

“Scalable Author Disambiguation for Bibliographic Databases”: The Leibniz-Gemeinschaft funds our new project on author disambiguation in large bibliographic databases. Project partners are the computer science bibliography DBLP at Schloss Dagstuhl and the Zentralblatt MATH, “the world’s most comprehensive and longest running abstracting and reviewing service in pure and applied mathematics” at FIZ Karlsruhe — 2015-2018.

PhD. Thesis Submitted

In October 2014 Angela Fahrni submitted her PhD. thesis, “Joint Discourse-aware Concept Disambiguation and Clustering”. In November 2014 Angela started as PostDoc at IBM Research in Z├╝rich.