I am PhD student in the Natural Language Understanding group at Idiap Research Institute and EPFL, under the supervision of James Henderson. I work on learning representations for sentences. Particular focus is on representations that model information abstraction. Eventually, I want to reuse them in applications that require abstract reasoning, such as opinion summarization.
During my master's studies, I worked as a student research assistant with Ansgar Scherp at Leibniz Information Centre for Economics - ZBW. I studied many different NLP-related topics, including topical document classification in digital libraries, text retrieval, and citation recommendation.
I received a BSc and MSc in Computer Science from Christian-Albrechts-Universitaet zu Kiel.
Mai, F., Galke, L. & Scherp, A. (2019). CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model. To appear in International Conference on Learning Representations 2019. PDF
Vagliano, I., Galke, L., Mai, F. & Scherp, A. (2018). Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation. In Proceedings of the ACM Recommender Systems Challenge 2018. PDF
Galke, L., Mai, F., Vagliano, I., & Scherp, A. (2018). Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels. In Proc. of ACM UMAP 2018. PDF
Using Deep Learning For Title-Based Semantic Subject Indexing To Reach Competitive Performance to Full-Text. In The 18 th ACM/IEEE Joint Conference on Digital Libraries. PDF
Galke, L., Mai, F., Schelten, A., Brunsch, D., & Scherp, A. (2017). Using Titles vs. Full-Text as Source for Automated Semantic Document Annotation. In Ninth International Conference on Knowledge Capture (K-CAP 2017). PDF
Saleh, A., Mai, F., Nishioka, C., & Scherp, A. (2017). Reranking-based Recommender System with Deep Learning. In Workshop on “Deep Learning in heterogenen Datenbeständen” at INFORMATIK 2017. PDF