Seminarium i datorlingvistik

  • Datum: –12.00
  • Plats: Engelska parken Rum: 9-3042
  • Föreläsare: Ekaterina Lapshinova-Koltunski
  • Kontaktperson: Ali Basirat
  • Seminarium

Cross-lingual Analysis of Coreference: Top-down vs. Bottom-up Approaches

In this talk, I will report on the ongoing work on discourse in a  multilingual context. I will present two case studies of coreference and  discourse-related phenomena that represent two approaches: (1) top-down  or theory-driven: here we start from some linguistic knowledge derived from the existing frameworks, define linguistic  categories to analyse and create an annotated corpus that can be used  either for further linguistic analysis or as training data for NLP  applications; (2) bottom-up or data-driven: in this case, we start from a set of features of shallow character that we believe are  discourse-related. We extract these structures from a huge amount of data and analyse them from a linguistic point of view trying to describe and explain the observed phenomena from the point of view of existing theories and grammars. Both cases studies are a  part of my joint work with Christian Hardmeier on coreference in  English and German.