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.

News

The Dark Side of Natural Language Processing

At the first “Ethics in Natural Language Processing” workshop in Valencia, scientists discussed the opportunities and dangers of automatic speech analysis. According to HITS researcher Michael Strube, “Exceedingly few people know how well we can analyze unstructured data.” Smartphones are a part of our everyday lives both at work and at home. We write emails,…

Details

Publication in Scientometrics Journal

A study entitled “Data Sets for Author Name Disambiguation: An Empirical Analysis and a New Resource” has just been published in the Springer Scientometrics journal. The authors of the study, which was produced in the Leibniz-funded project “Scalable Author Disambiguation for Bibliographic Databases”, are Mark-Christoph Müller from the HITS NLP group, Florian Reitz from dblp…

Details