I am currently a Machine Learning Engineer at Apple. Prior to this I was a PhD Student and PostDoc at LMU Munich under the supervision of Prof. Dr. Hinrich Schütze. My current research interests are: multilingual NLP, representation learning, low-resource processing, interpretability of embeddings, position encodings.
Wine is not v i n. On the Compatibility of Tokenizations across Languages emnlp 2021 - findings. [Paper] * equal contribution
Graph Algorithms for Multiparallel Word Alignment emnlp 2021. [Paper] * equal contribution
BERT Cannot Align Characters insights21 workshop (collocated with emnlp21) [Paper]
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus acl 2021 - demos. [Paper] [Code]
Static Embeddings as Efficient Knowledge Bases? naacl 2021. [Paper] [Code] * equal contribution
Position Information in Transformers: An Overview. arxiv 2021. [Paper] * equal contribution
Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models. eacl 2021. - best short paper award [Paper] [Data] [Code] * equal contribution
Semantic Text Segment Classification of Structured Technical Content. nlbd 2021. [Paper]
Locating Language-Specific Information in Contextualized Embeddings. arxiv 2021. [Paper]
Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention. coling 2020. [Paper] [Code]
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations. coling 2020. [Paper]
Modeling Graph Structure via Relative Position for Better Text Generation from Knowledge Graphs. textgraphs-15 workshop (collocated with naacl21). [Paper]
Identifying Necessary Elements for BERT’s Multilinguality. emnlp 2020. [Paper] [Code]
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings. emnlp-findings 2020. [Paper] [Code] [Demo] * equal contribution
Subword Sampling for Low Resource Word Alignment. arxiv 2020. [Paper]
Quantifying the Contextualization of Word Representations with Semantic Class Probing. emnlp-findings 2020. [Paper]
Analytical Methods for Interpretable Ultradense Word Embeddings. emnlp 2019. [Paper] [Code] [Supplementary] [Presentation]
Multilingual Embeddings Jointly Induced from Contexts and Concepts: Simple, Strong and Scalable. arxiv 2018. [Paper]
Embedding Learning through Multilingual Concept Induction. acl 2018. [Paper] [Poster] [Resources]
Branch-and-Cut Algorithms for the Distributionally Robust Capacitated Vehicle Routing Problem. [Paper which is partly based on the thesis.]
Positively Excited Random Walks on Integers.
A Comparative Study of Positional Information in Self-Attention Artificial Neural Networks. 2020.
Semantic Text Classification Using Deep Learning. 2020.
Predicting Commonsense Knowledge Using Pretrained Language Models. 2020.
Neural Methods in Document Similarity Detection and Information Retrieval. 2019.
Cross-Lingual Named Entity Recognition. 2019.
Webcrawling of a Bavarian low-resource corpus. 2019.
Teaching Assistent for "Basics of Computational Linguistics". 2018/2019.
Deep Learning for Text Classification. 2018.
Machine Learning for Automated Detection of Fake News. 2018.
Deep Learning for Extraction of Opinion Entities. 2017.
Teaching Assistent for "Probability Theory". 2014.
Teaching Assistent for "Mathematics II". 2013/2014.
Reviewer at ACL21, NAACl21, EACL21, EMNLP20, COLING20, ACL19, NAACL18, EMNLP18
2021 Berlin Machine Learning Meetup
2021 Conference on Hate Speech Detection Hildesheim
2020 EMNLP Main conference / SIGTYP workshop
2019 EMNLP Main conference
2019 Applied.ai
2019 Munich Datageeks Meetup