Shigehiko Schamoni, M.A.
「シャモニ滋彦」
In May 2023 I started a new position as Compute Lab Manager at the Institute of Computer Engineering (ZITI) at Heidelberg University. I am responsible for planning, extending, and optimizing the scientific compute infrastruture of various research groups at the institute.
Currently, I’m finishing my PhD thesis under supervision of Prof. Dr. Stefan Riezler at the Statistical NLP group of Heidelberg University.
Research Interests
- Cluster Computing / HPC
- Medical Data Analysis
- Speech Translation
- Grounding in Machine Translation
- Cross-Language Information Retrieval
Publications
- Clinical expert-assigned ground truth for sepsis prediction on admission to the ICUJournal of Critical Care, 81, 154547, 2024
@article{holkeETAL24, title = {Clinical expert-assigned ground truth for sepsis prediction on admission to the ICU}, author = {Holke, Franziska and Hahn, Bianka and Lindner, Holger A. and Schamoni, Shigehiko and Krebs, Jörg and Nitsch, Stephanie and Friedrich, Thomas and Schwarz, Anke and Graf, Peter Tobias and Thiel, Manfred and Schneider-Lindner, Verena}, journal = {Journal of Critical Care}, volume = {81}, pages = {154547}, year = {2024}, issn = {0883-9441}, doi = {10.1016/j.jcrc.2024.154547}, url = {https://www.sciencedirect.com/science/article/pii/S0883944124000340}, }
- Validity problems in clinical machine learning by indirect data labeling using consensus definitionsMachine Learning for Health (ML4H@NeurIPS 2023) Findings Track, ML4H, New Orleans, LA, USA, 2023
@inproceedings{hagmannETAL23, title = {Validity problems in clinical machine learning by indirect data labeling using consensus definitions}, author = {Hagmann, Michael and Schamoni, Shigehiko and Riezler, Stefan}, year = {2023}, journal = {Machine Learning for Health (ML4H@NeurIPS 2023) Findings Track}, organization = {ML4H}, publisher = {ML4H}, city = {New Orleans, LA}, country = {USA}, url = {https://arxiv.org/abs/2311.03037}, }
- Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and TranslationIEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP), Rhodes Island, Greece, 2023
@inproceedings{lamETAL2023, author = {Lam, Tsz Kin and Schamoni, Shigehiko and Riezler, Stefan}, title = {Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation}, journal = {IEEE International Conference on Acoustics, Speech and Signal Processing}, journal-abbrev = {ICASSP}, year = {2023}, city = {Rhodes Island}, country = {Greece}, url = {https://arxiv.org/abs/2210.15398}, }
- Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of SepsisProceedings of the 6th Machine Learning for Healthcare Conference (Proceedings of Machine Learning Research), 182, PMLR, Durham, NC, USA, 2022
@inproceedings{schamoni2022, author = {Schamoni, Shigehiko and Hagmann, Michael and Riezler, Stefan}, title = {Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of Sepsis}, booktitle = {Proceedings of the 6th Machine Learning for Healthcare Conference}, year = {2022}, city = {Durham, NC}, country = {USA}, volume = {182}, series = {Proceedings of Machine Learning Research}, month = {05--06 Aug}, publisher = {PMLR}, url = {https://proceedings.mlr.press/v182/schamoni22a/schamoni22a.pdf}, }
- Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech TranslationProceedings of the 60th Annual Meeting of the Association for Computational Linguistics, (ACL), Dublin, Ireland, 2022
@inproceedings{lamETAL2022, author = {Lam, Tsz Kin and Schamoni, Shigehiko and Riezler, Stefan}, title = {Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation}, journal = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics}, journal-abbrev = {ACL}, year = {2022}, city = {Dublin}, country = {Ireland}, url = {https://arxiv.org/abs/2203.08757}, }
- Ground truth labels challenge the validity of sepsis consensus definitions in critical illnessJournal of Translational Medicine, 20(6), 27, 2022
@article{lindnerETAL2022, author = {Lindner, H. A. and Schamoni, S. and Kirschning, T. and Worm, C. and Hahn, B. and Centner, F. S. and Schoettler, J. J. and Hagmann, M. and Krebs, J. and Mangold, D. and Nitsch, S. and Riezler, S. and Thiel, M. and Schneider-Lindner, V.}, title = {Ground truth labels challenge the validity of sepsis consensus definitions in critical illness}, journal = {Journal of Translational Medicine}, year = {2022}, volume = {20}, number = {6}, pages = {27}, doi = {10.1186/s12967-022-03228-7}, url = {https://doi.org/10.1186/s12967-022-03228-7}, }
- On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASRProceedings of the 22th Annual Conference of the International Speech Communication Association, (INTERSPEECH), Brno, Czech Republic, 2021
@inproceedings{lamETAL2021, author = {Lam, Tsz Kin and Ohta, Mayumi and Schamoni, Shigehiko and Riezler, Stefan}, title = {On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR}, journal = {Proceedings of the 22th Annual Conference of the International Speech Communication Association}, journal-abbrev = {INTERSPEECH}, year = {2021}, city = {Brno}, country = {Czech Republic}, url = {https://arxiv.org/abs/2104.01393}, }
- Cascaded Models With Cyclic Feedback For Direct Speech TranslationIEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP), 2021
@inproceedings{lamETAL2020, author = {Lam, Tsz Kin and Schamoni, Shigehiko and Riezler, Stefan}, year = {2021}, title = {Cascaded Models With Cyclic Feedback For Direct Speech Translation}, journal = {IEEE International Conference on Acoustics, Speech and Signal Processing}, journal-abbrev = {ICASSP}, url = {http://arxiv.org/abs/2010.11153}, }
- Embedding Meta-Textual Information for Improved Learning to RankProceedings of the 28th International Conference on Computational Linguistics, (COLING), Barcelona, Spain, 2020
@inproceedings{kuwaETAL2020, author = {Kuwa, Toshitaka and Schamoni, Shigehiko and Riezler, Stefan}, year = {2020}, title = {Embedding Meta-Textual Information for Improved Learning to Rank}, journal = {Proceedings of the 28th International Conference on Computational Linguistics}, journal-abbrev = {COLING}, city = {Barcelona, Spain}, url = {http://arxiv.org/abs/2010.16313}, }
- Leveraging Implicit Expert Knowledge for Non-Circular Machine Learning in Sepsis PredictionJournal of Artificial Intelligence in Medicine, 2019 (Preprint)
@article{schamoniETAL19, title = {Leveraging Implicit Expert Knowledge for Non-Circular Machine Learning in Sepsis Prediction}, author = {Schamoni, Shigehiko and Lindner, Holger A. and Schneider-Lindner, Verena and Thiel, Manfred and Riezler, Stefan}, journal = {Journal of Artificial Intelligence in Medicine}, year = {2019}, note = {Preprint}, url = {https://arxiv.org/pdf/1909.09557.pdf}, }
- Multidrug-Resistant Bacteria and Disease Progression in Patients with End-Stage Liver Disease and after Liver TransplantationJ Gastrointestin Liver Dis, 28(3), 303–310, 2019
@article{friedrichETAL19, author = {Friedrich, K. and Krempl, J. and Schamoni, S. and Hippchen, T. and Pfeiffenberger, J. and Rupp, C. and Gotthardt, D. N. and Houben, P. and Von Haken, R. and Heininger, A. and Brenner, T. and Mehrabi, A. and Weiss, K. H. and Mieth, M.}, title = {{{M}ultidrug-{R}esistant {B}acteria and {D}isease {P}rogression in {P}atients with {E}nd-{S}tage {L}iver {D}isease and after {L}iver {T}ransplantation}}, journal = {J Gastrointestin Liver Dis}, year = {2019}, volume = {28}, number = {3}, pages = {303--310}, month = sep, url = {https://www.jgld.ro/jgld/index.php/jgld/article/view/212/143}, }
- Interactive-Predictive Neural Machine Translation through Reinforcement and ImitationProceedings of the Machine Translation Summit, (MTSUMMIT XVII), Dublin, Ireland, 2019
@inproceedings{lam2019, author = {Lam, Tsz Kin and Schamoni, Shigehiko and Riezler, Stefan}, title = {Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation}, journal = {Proceedings of the Machine Translation Summit}, journal-abbrev = {MTSUMMIT XVII}, year = {2019}, city = {Dublin}, country = {Ireland}, url = {http://www.cl.uni-heidelberg.de/~riezler/publications/papers/MTSUMMIT2019.pdf}, }
- Cross-lingual Learning-to-Rank with Shared RepresentationsProceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Industry Track, (NAACL-HLT), New Orleans, LA, USA, 2018
@inproceedings{sasaki2018, author = {Sasaki, Shota and Sun, Shuo and Schamoni, Shigehiko and Duh, Kevin and Inui, Kentaro}, title = {Cross-lingual Learning-to-Rank with Shared Representations}, journal = {Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Industry Track}, journal-abbrev = {NAACL-HLT}, year = {2018}, city = {New Orleans, LA}, country = {USA}, url = {http://www.cl.uni-heidelberg.de/~schamoni/publications/dl/NAACL2018a.pdf}, }
- A Dataset and Reranking Method for Multimodal MT of User-Generated Image CaptionsProceedings of the 13th biennial conference of the Association for Machine Translation in the Americas, (AMTA), Boston, MA, USA, 2018
@inproceedings{schamoni2018, author = {Schamoni, Shigehiko and Hitschler, Julian and Riezler, Stefan}, title = {A Dataset and Reranking Method for Multimodal MT of User-Generated Image Captions}, journal = {Proceedings of the 13th biennial conference of the Association for Machine Translation in the Americas}, journal-abbrev = {AMTA}, year = {2018}, city = {Boston, MA}, country = {USA}, url = {http://www.cl.uni-heidelberg.de/~riezler/publications/papers/AMTA2018.1.pdf}, }
- Multimodal Pivots for Image Caption TranslationProceedings of the 54th Annual Meeting of the Association for Computational Linguistics, (ACL), Berlin, Germany, 2016
@inproceedings{hitschler2016a, author = {Hitschler, Julian and Schamoni, Shigehiko and Riezler, Stefan}, title = {Multimodal Pivots for Image Caption Translation}, journal = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics}, journal-abbrev = {ACL}, year = {2016}, city = {Berlin}, country = {Germany}, url = {http://www.cl.uni-heidelberg.de/~riezler/publications/papers/ACL2016.2.pdf}, }
- QUality Estimation from ScraTCH (QUETCH): Deep Learning for Word-level Translation Quality EstimationProceedings of the 10th Workshop on Machine Translation, (WMT), Lisbon, Portugal, 2015
@inproceedings{kreutzer2015, author = {Kreutzer, Julia and Schamoni, Shigehiko and Riezler, Stefan}, title = {QUality Estimation from ScraTCH (QUETCH): Deep Learning for Word-level Translation Quality Estimation}, journal = {Proceedings of the 10th Workshop on Machine Translation}, journal-abbrev = {WMT}, year = {2015}, city = {Lisbon}, country = {Portugal}, url = {http://www.cl.uni-heidelberg.de/~riezler/publications/papers/WMT2015.pdf}, }
- Combining Orthogonal Information in Large-Scale Cross-Language Information RetrievalProceedings of the 38th Annual ACM SIGIR Conference, (SIGIR), Santiago, Chile, 2015
@inproceedings{schamoni2015, author = {Schamoni, Shigehiko and Riezler, Stefan}, title = {Combining Orthogonal Information in Large-Scale Cross-Language Information Retrieval}, journal = {Proceedings of the 38th Annual ACM SIGIR Conference}, journal-abbrev = {SIGIR}, year = {2015}, city = {Santiago}, country = {Chile}, url = {http://www.cl.uni-heidelberg.de/~riezler/publications/papers/SIGIR2015.pdf}, }
- Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language RetrievalProceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, (ACL), Baltimore, MD, USA, 2014
@inproceedings{schamoni2014, author = {Schamoni, Shigehiko and Hieber, Felix and Sokolov, Artem and Riezler, Stefan}, title = {Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language Retrieval}, journal = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics}, journal-abbrev = {ACL}, year = {2014}, city = {Baltimore, MD}, country = {USA}, url = {https://www.cl.uni-heidelberg.de/~riezler/publications/papers/ACL2014short.pdf}, }
Teaching
- Summer term 2024
- Co-Instructor; graduate course “Tools – Werkzeuge für effizientes wissenschaftliches Arbeiten”
- Summer term 2023
- Co-Instructor; graduate course “Tools – Werkzeuge für effizientes wissenschaftliches Arbeiten”
- Winter term 2021/22
- Instructor; undergraduate course “Einführung in die Nutzung computerlinguistischer Ressourcen”
- Summer term 2015
- Instructor; undergraduate/graduate course “Advanced Programming”
- Winter term 2014/15
- Instructor; undergraduate course “Mathematischer Vorkurs”
- Summer term 2014
- Instructor; undergraduate course “Parallel Programming Paradigms”
- Summer term 2013
- Instructor; undergraduate/graduate course “Advanced Programming”
- Instructor; undergraduate course “Mathematischer Vorkurs”
- Winter term 2012/13
- Instructor; undergraduate course “Statistical Methods for Computational Linguistics”
- Instructor; undergraduate course “Einführung in die Nutzung computerlinguistischer Ressourcen”
- Summer term 2012
- Instructor; undergraduate/graduate course “Advanced Programming”
- Instructor; undergraduate course “Einführung in die Nutzung computerlinguistischer Ressourcen”
- Summer term 2011
- Teaching Assistant; undergraduate course “Einführung in die lineare Algebra und Optimierung für Computerlinguistik”
Consultation Hours
By appointment only. Please contact me via email.