Photo

Octavian Eugen Ganea

E-mail: octavian.ganea at inf.ethz.ch
Office: ETH Zürich, CAB F 42.1

Resume: PDF, Linkedin

I am a doctoral student in the Data Analytics Lab at ETH Zürich, working with prof. Thomas Hofmann.

Research interests:

I am broadly interested in representation learning for text, graphs or images through statistical or geometric models that could be devised and understood in a mathematically principled manner. In particular, I have recently explored finding and learning latent hierarchical structures in data via hyperbolic geometry.

Interested in: Representation Learning, Hierarchical Structures, Natural Language Processing, Neural Networks and Deep Learning, Word and Entity Embeddings, Probabilistic Graphical Models, Structured Prediction

Publications

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities
Octavian-Eugen Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn.
[Paper]


Photo
Hyperbolic Neural Networks
Octavian-Eugen Ganea*, Gary Bécigneul*, Thomas Hofmann.
Full paper @ NIPS 2018: Conference on Neural Information Processing Systems. Spotlight (top 4% of all submitted papers).
[Paper] [Video] [Poster] [BLOG] [Data + Code]





Photo
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann.
Full paper @ ICML 2018: International Conference on Machine Learning. Oral talk.
[PDF] [Slides] [Poster] [Data + Code]






Photo
End-to-end Neural Entity Linking
Nikolaos Kolitsas*, Octavian-Eugen Ganea*, Thomas Hofmann.
Full paper @ CoNLL 2018: Conference on Natural Language Learning. Poster.
[PDF] [Data + Code]





Photo
Poincaré GloVe: Hyperbolic Word Embeddings
Alexandru Tifrea*, Gary Bécigneul*, Octavian-Eugen Ganea*
Full paper @ ICLR'19: International Conference on Learning Representations.
[PDF] [Data + Code]





Photo
Riemannian Adaptive Optimization Methods
Gary Bécigneul, Octavian-Eugen Ganea
Full paper @ ICLR'19: International Conference on Learning Representations.
[PDF]





Photo
Deep Joint Entity Disambiguation with Local Neural Attention
Octavian-Eugen Ganea, Thomas Hofmann.
Full paper @ EMNLP 2017: Conference on Empirical Methods in Natural Language Processing. Poster
[PDF] [Slides] [Poster] [Data + Code]





Photo
Probabilistic Bag-Of-Hyperlinks Model for Entity Linking
Octavian-Eugen Ganea, Marina Ganea, Aurelien Lucchi, Carsten Eickhoff, Thomas Hofmann.
Full paper @ WWW 2016: International World Wide Web Conference. Oral talk.
[PDF] [Slides] [Poster] [Data + Code] [Online system (Gerbil - D2KB)] [Comparison with existing systems (Jan 2018)]



Learning and Evaluating Sparse Interpretable Sentence Embeddings
Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, Thomas Hofmann.
EMNLP'18 Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. 2018. .
[PDF]


Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
Till Haug, Octavian-Eugen Ganea, Paulina Grnarova .
Short paper @ ECIR 2018: European Conference on Information Retrieval .
[PDF] [Slides]


Web2Text: Deep Structured Boilerplate Removal
Thijs Vogels, Octavian-Eugen Ganea, Carsten Eickhoff .
Long paper @ ECIR 2018: European Conference on Information Retrieval .
[PDF] [Slides] [Source Code]


Community service

Reviewer at ACL 2018 and EMNLP 2018.

Teaching

Check out the currently available student projects in our group.
Supervised Theses/Projects:
Alexandru Tifrea: Hyperbolic Word Embeddings,
MSc thesis (jointly with Gary Becigneul), ETH, April - October 2018
Kolitsas Nikolaos: End-to-end Neural Entity Linking,
MSc thesis, ETH, October 2017 - April 2018
Junlin Yao: Detecting Medication and Adverse Drug Events from Electronic Health Records,
MSc thesis (jointly with Carsten Eickhoff), ETH, September 2017 - March 2018
Igor Petrovski: Hyperbolic Sentence Embeddings,
MSc thesis (jointly with Gary Becigneul), ETH, October 2017 - April 2018
Valentin Trivonov: Sparse and Interpretable Embeddings,
MSc thesis (jointly supervised with Anna Potapenko), ETH, December 2017 - May 2018
Andreas Hess: Reinforcement Learning for Question Answering with Semi-structured Tables,
MSc thesis, ETH, December 2016 - May 2017
Yifan Su: Deep Structured Prediction for Joint Entity Linking and Coreference Resolution,
MSc thesis (jointly supervised with Aurelien Lucchi), ETH, July - December 2016
Till Haug: Convolutional and Recursive Neural Networks for Question Answering on Semi-structured Tables ,
BSc thesis (jointly supervised with Paulina Grnarova), ETH, August 2016 - January 2017
Severin Bahman: Memory Networks for Entity Linking,
Research project (jointly supervised with Aurelien Lucchi), ETH, March - July 2016
Andreas Georgiadis: Learning Sentence and Entity Representations for Question Answering,
Research project (jointly supervised with Aurelien Lucchi), ETH, March - July 2016
Thijs Vogels: Structured Prediction for Web Page Content Extraction,
Research project (jointly supervised with Carsten Eickhoff), ETH, Sep 2015 - May 2016
Monteiro Freire Ribeiro João Pedro: Unsupervised Knowledge Base Fact Prediction using Matrix Word Embeddings,
BSc thesis (jointly supervised with Paulina Grnarova), ETH, Nov 2015 - May 2016
Teaching assistant:
Deep Learning: Fall 2017, 2018
Computational Intelligence Lab: Spring 2015, 2016, 2017, 2018
Information retrieval: Fall 2014, 2015, 2016
Advanced Algorithms (EPFL): Fall 2011
Numerical Methods (UPB): Fall 2008,2009

Tutorials

The mathematics of the expectation maximization algorithm
Learning in pairwise conditional random fields