Follow
Sebastian Hofstätter
Sebastian Hofstätter
Research Scientist @ Cohere
Verified email at tuwien.ac.at - Homepage
Title
Cited by
Cited by
Year
Efficiently teaching an effective dense retriever with balanced topic aware sampling
S Hofstätter, SC Lin, JH Yang, J Lin, A Hanbury
Proceedings of the 44th International ACM SIGIR Conference on Research and …, 2021
3032021
Improving efficient neural ranking models with cross-architecture knowledge distillation
S Hofstätter, S Althammer, M Schröder, M Sertkan, A Hanbury
arXiv preprint arXiv:2010.02666, 2020
1882020
Local self-attention over long text for efficient document retrieval
S Hofstätter, H Zamani, B Mitra, N Craswell, A Hanbury
Proceedings of the 43rd International ACM SIGIR Conference on Research and …, 2020
872020
Interpretable & time-budget-constrained contextualization for re-ranking
S Hofstätter, M Zlabinger, A Hanbury
arXiv preprint arXiv:2002.01854, 2020
862020
Let's measure run time! Extending the IR replicability infrastructure to include performance aspects
S Hofstätter, A Hanbury
Proceedings of the Open-Source IR Replicability Challenge (OSIRRC 2019) co …, 2019
52*2019
Intra-document cascading: learning to select passages for neural document ranking
S Hofstätter, B Mitra, H Zamani, N Craswell, A Hanbury
Proceedings of the 44th International ACM SIGIR Conference on Research and …, 2021
432021
On the Effect of Low-Frequency Terms on Neural-IR Models
S Hofstätter, N Rekabsaz, C Eickhoff, A Hanbury
Proceedings of the 42nd International ACM SIGIR Conference on Research and …, 2019
412019
Fid-light: Efficient and effective retrieval-augmented text generation
S Hofstätter, J Chen, K Raman, H Zamani
Proceedings of the 46th International ACM SIGIR Conference on Research and …, 2023
352023
Conformer-kernel with query term independence for document retrieval
B Mitra, S Hofstatter, H Zamani, N Craswell
arXiv preprint arXiv:2007.10434, 2020
282020
Introducing neural bag of whole-words with colberter: Contextualized late interactions using enhanced reduction
S Hofstätter, O Khattab, S Althammer, M Sertkan, A Hanbury
Proceedings of the 31st ACM International Conference on Information …, 2022
272022
TU Wien@ TREC Deep Learning'19--Simple Contextualization for Re-ranking
S Hofstätter, M Zlabinger, A Hanbury
arXiv preprint arXiv:1912.01385, 2019
182019
Enriching word embeddings for patent retrieval with global context
S Hofstätter, N Rekabsaz, M Lupu, C Eickhoff, A Hanbury
Advances in Information Retrieval: 41st European Conference on IR Research …, 2019
182019
Mitigating the position bias of transformer models in passage re-ranking
S Hofstätter, A Lipani, S Althammer, M Zlabinger, A Hanbury
Advances in Information Retrieval: 43rd European Conference on IR Research …, 2021
172021
Cross-domain retrieval in the legal and patent domains: a reproducibility study
S Althammer, S Hofstätter, A Hanbury
Advances in Information Retrieval: 43rd European Conference on IR Research …, 2021
172021
PARM: A paragraph aggregation retrieval model for dense document-to-document retrieval
S Althammer, S Hofstätter, M Sertkan, S Verberne, A Hanbury
European Conference on Information Retrieval, 19-34, 2022
162022
Establishing strong baselines for tripclick health retrieval
S Hofstätter, S Althammer, M Sertkan, A Hanbury
European Conference on Information Retrieval, 144-152, 2022
112022
Fine-grained relevance annotations for multi-task document ranking and question answering
S Hofstätter, M Zlabinger, M Sertkan, M Schröder, A Hanbury
Proceedings of the 29th ACM International Conference on Information …, 2020
102020
Linguistically informed masking for representation learning in the patent domain
S Althammer, M Buckley, S Hofstätter, A Hanbury
arXiv preprint arXiv:2106.05768, 2021
92021
Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling
S Hofstätter, J Chen, K Raman, H Zamani
ICML 2022 Workshop on Knowledge Retrieval and Language Models (KRLM @ ICML ’22), 2022
82022
TripJudge: A Relevance Judgement Test Collection for TripClick Health Retrieval
S Althammer, S Hofstätter, S Verberne, A Hanbury
Proceedings of the 31st ACM International Conference on Information …, 2022
72022
The system can't perform the operation now. Try again later.
Articles 1–20