About me

I am a postdoc in the Natural Language Understanding Group at Idiap. Since September 2022, I'm also a lecturer in NLP and MLOps at the Lucerne University of Applied Sciences and Arts. My interests lie in summarization, hallucination detection, generation and deep learning for NLP in general. I'm funded by an SNF Sinergia grant on the automated interpretation of political and economic policy documents.

Short bio

I received both my BSc (2011) and MSc (2013) in Computer Science from ETH Zürich. After that, I helped start a health data platform MIDATA.coop and was the first employee of 1plusX. I then joined the Data Analytics Lab at ETH Zürich as a PhD student for two years before moving to Idiap in autumn 2018. I received my PhD from EPFL in June 2023.

Publications

Andreas Marfurt, 2023. Interpretable Representation Learning and Evaluation for Abstractive Summarization. PhD thesis at EPFL. [info] [pdf] [bibtex]

Andreas Marfurt, Ashley Thornton, David Sylvan, Lonneke van der Plas and James Henderson, 2022. A Corpus and Evaluation for Predicting Semi-Structured Human Annotations. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), EMNLP 2022. [pdf] [bibtex] [video] [code]

Andreas Marfurt and James Henderson, 2022. Unsupervised Token-level Hallucination Detection from Summary Generation By-products. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), EMNLP 2022. [pdf] [bibtex] [video] [teaser video (1 min)] [code]

Andreas Marfurt and James Henderson, 2021. Sentence-level Planning for Especially Abstractive Summarization. In Proceedings of the Third Workshop on New Frontiers in Summarization, EMNLP 2021. [pdf] [bibtex] [video] [code]

Google scholar

https://scholar.google.ch/citations?user=VdR7ECMAAAAJ

 

---

Tel: +41277217448
Office: 306-9a
Contact

© Idiap Research Institute 2017-