Sebastian Hofstätter

Information Retrieval Machine Learning Neural Re-Ranking

Hi, I am Sebastian, PhD student and research assistant at TU Wien supervised by Prof. Allan Hanbury. I work on neural re-ranking models – I try to make them fast, while still providing good effectiveness. Additionally, I work on tools and methods to explain the behavior of neural re-ranking models.

Find me on Twitter and GitHub or contact me: sebastian.hofstaetter@tuwien.ac.at

Publications


Google Scholar

2019TREC TU Wien @ TREC Deep Learning ’19 – Simple Contextualization for Re-ranking
S. Hofstätter, M. Zlabinger, and A. Hanbury
2019SIGIR On the Effect of Low-Frequency Terms on Neural-IR Models
S. Hofstätter, N. Rekabsaz, C. Eickhoff, and A. Hanbury
2019OSIRRC Let’s measure runtime!
S. Hofstätter and A. Hanbury
2019ECIR Enriching Word Embeddings for Patent Retrieval with Global Context
S. Hofstätter, N. Rekabsaz, M. Lupu, C. Eickhoff, and A Hanbury
⭐ Won best systems short paper award

Teaching

Advanced Information Retrieval (Summer 2019)
Lectures: Crash course IR, Neural Networks for NLP, Neural IR
Exercise: Implement neural re-ranking models in PyTorch

Introduction to Information Retrieval (Winter 2018, 2019)
Lectures: Inverted Index, Scoring models, Efficient & fast text processing
Exercise: Implement an efficient search engine from scratch

All my materials are available on GitHub

Education

2018 - presentPhD - Computer Science - TU Wien 2016 - 2018Master's - Software Engineering - TU Wien 2012 - 2016Bachelor's - Computer Science and Economics - TU Wien