Some tough and strange problems in automatic summarisation

Abstract:

Automatic summarisation, extractive and abstractive, is a tough task both conceptually and computationally.  In this talk I will survey some of the challenges in defining the automatic summarisation task, and how it corresponds to our data and our evaluation methods.  In particular, I discuss some central caveats of summarisation, incurred in the use of the ROUGE metric for evaluation, with respect to optimal and/or human solutions.  I also give some preliminary outlook for future definition of the problem, given these findings.

Bio:

Natalie Schluter is Associate Professor and Head of the Data Science BSc Programme at the IT University of Copenhagen. Her research is in the overlap of Algorithms, NLP and Machine Learning. She holds a number of degrees in Linguistics and Mathematics, receiving her PhD in NLP from Dublin City University, and having spent some years in Industry with the SAS Institute and as Chief Analyst at Danske Bank. Natalie is a Canadian, living in Denmark for the past 9 years with her husband and two children.