Michael Fell

PhD student in Computer Science

Michael Fell is a PhD candidate in Computer Science at the Université Côte d'Azur working in the WIMMICS team of Inria Sophia-Antipolis, I3S laboratory.

He is currently (2017-2020) working on his PhD thesis on "Natural Language Processing of Song Lyrics" under the supervision of Elena Cabrio and Fabien Gandon.

As a Software Engineer in the automotive sector (2014-2017) he has worked on a prototype of a next-gen natural language dialogue system for in-car use. There, he mostly programmed in Java, while nowadays he is using Python predominantly.

Michael Fell graduated in Computational Linguistics at the University of Saarland, Saarbrücken, Germany. He conducted his master thesis titled "Lyrics Classification" under the supervision of Caroline Sporleder, defended in January 2014.

Research Interests

Natural Language Processing

Machine Learning

Text Segmentation

Classification

Artificial Intelligence

Text Summarization

Publications

2019

Michael Fell, Elena Cabrio, Fabien Gandon, Alain Giboin. Comparing Automated Methods to Detect Explicit Content in Song Lyrics. In Proceedings of the Conference on Recent Advances in Natural Language Processing (RANLP '19), Varna, Bulgaria. pp.328-337.

Michael Fell, Elena Cabrio, Michele Corazza, Fabien Gandon. Song Lyrics Summarization Inspired by Audio Thumbnailing. In Proceedings of the Conference on Recent Advances in Natural Language Processing (RANLP '19), Varna, Bulgaria. pp.338-344.

2018

Michael Fell, Yaroslav Nechaev, Elena Cabrio, Fabien Gandon. Lyrics Segmentation: Textual Macrostructure Detection using Convolutions. In Proceedings of the Conference on Computational Linguistics (COLING '18), Santa Fe, New Mexico, United States. pp.2044-2054.

Diego Monti, Enrico Palumbo, Giuseppe Rizzo, Pasquale Lisena, Raphaël Troncy, Michael Fell, Elena Cabrio, Maurizio Morisio. An Ensemble Approach of Recurrent Neural Networks using Pre-Trained Embeddings for Playlist Completion. Proceedings of the ACM Recommender Systems Challenge 2018 (RecSys Challenge '18). ACM, New York, United States.

2014

Michael Fell, Caroline Sporleder. Lyrics-based analysis and classification of music. In Proceedings of the Conference on Computational Linguistics (COLING '14), Dublin, Ireland. pp.620-631.

Contact

Address
Polytech'Nice-Sophia
Site des Templiers
930, Route des Colles
Bureau 416
06560 Sophia-Antipolis, FRANCE
Phone Number
+33 666 221 349
Email
michael.fell@inria.fr