Scholar
Adam Wiemerslage
Google Scholar ID: T-_ceXcAAAAJ
Kensho
Citations & Impact
Citations
138
H-index
6
i10-index
4
Publications
17
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - September 2024, EMNLP 2024 accepted paper: 'Getting The Most Out of Your Training Data: Exploring Unsupervised Tasks for Morphological Inflection'.
- - January 2024, EACL 2024 accepted paper: 'Quantifying the Hyperparameter Sensitivity of Neural Networks for Character-level Sequence-to-Sequence Tasks'.
- - May 2023, Findings of ACL 2023 accepted paper: 'An Investigation of Noise in Morphological Inflection'.
- - October 2022, EMNLP 2022 accepted paper: 'A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection'.
- - March 2022, Findings of ACL 2022 accepted paper: 'Morphological Processing of Low-Resource Languages: Where We Are and What's Next'.
- - August 2021, published paper on the results of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering.
Research Experience
- Worked as a research scientist at Pearson on NLP research; was a researcher at the US Army Research Laboratory; worked as a software engineer at several companies; interned at Apple in May 2024, focusing on detecting cognitive decline from speech.
Education
- PhD student in Computer Science at The University of Colorado, Boulder, under the supervision of Katharina von der Wense, expected to defend dissertation in April 2025.
Background
- Research Interests: NLP systems, particularly for underrepresented languages and computational morphology; using unsupervised and semi-supervised machine learning methods, and training deep learning models on very sparse datasets. Currently focused on reinforcement learning to align unsupervised training data with particular supervised tasks, and how better tokenization can enable multilingual LMs to perform well for underrepresented languages.
Miscellany
- Personal Interests: Outdoor activities.
