Word Embeddings for Practical Information Retrieval
Lukas Galke, Ahmed Saleh, Ansgar Scherp, "Word Embeddings for Practical Information Retrieval." INFORMATIK, 2017.
Curriculum Vitae
Education
- Ph.D in Computer Science, Kiel University, Germany, 2022 (expected)
- M.Sc. in Computer Science, Kiel University, Germany, 2017
- B.Sc. in Computer Science, Kiel University, Germany, 2013
Work experience
- 2022-today: Postdoctoral Researcher
- Max Planck Institute for Psycholinguistics
- Research on emergent communication with deep nets
- Group: LEADS group led by Limor Raviv
- 2018-2021: Doctoral Researcher
- ZBW — Leibniz Information Centre for Economics, Kiel and Hamburg, Germany
- Research on Deep Learning methods for dynamic network analysis. Interdisciplinary research on the scientific, economic, societal impacts of science dynamics
- Project: Q-AKTIV
- 2017-2020: Doctoral Researcher
- Kiel University, Germany
- Research in natural language processing and graph neural networks
- Teaching assistant for courses on Bachelor and Master level. Co-supervision of Bachelor/Master’s theses and student projects. State funding.
- Supervisor: Ansgar Scherp
- 2017-2018: Doctoral Researcher
- ZBW — Leibniz Information Centre for Economics, Kiel and Hamburg, Germany
- Research in natural language processing and recommender systems
- Project: Linked Open Citation Database
- Supervisor: Ansgar Scherp
- 2016-2017: Research Assistant (as M.Sc. student)
- ZBW — Leibniz Information Centre for Economics, Kiel and Hamburg, Germany
- Research on text classification and information retrieval.
- Supervisor: Ansgar Scherp
- 2014-2016: Various Student Assistant Jobs
- Kiel University, Germany
Keywords
- Machine Learning
- Natural Language Processing
- Emergent Communication
Publications
Using Titles vs. Full-text as Source for Automated Semantic Document Annotation
Lukas Galke, Florian Mai, Alan Schelten, Dennis Brunsch, Ansgar Scherp, "Using Titles vs. Full-text As Source for Automated Semantic Document Annotation." Knowledge Capture Conference, 2017.
Linked Open Citation Database: Enabling Libraries to Contribute to an Open and Interconnected Citation Graph
Anne Lauscher, Kai Eckert, Lukas Galke, Ansgar Scherp, Syed Rizvi, Sheraz Ahmed, Andreas Dengel, Philipp Zumstein, Annette Klein, "Linked Open Citation Database: Enabling Libraries to Contribute to an Open and Interconnected Citation Graph." 18th ACM/IEEE on Joint Conference on Digital Libraries, 2018.
Performance Comparison of Ad-Hoc Retrieval Models over Full-Text vs. Titles of Documents
Ahmed Saleh, Tilman Beck, Lukas Galke, Ansgar Scherp, "Performance Comparison of Ad-Hoc Retrieval Models over Full-Text vs. Titles of Documents." Maturity and Innovation in Digital Libraries, 2018.
Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation
Iacopo Vagliano, Lukas Galke, Florian Mai, Ansgar Scherp, "Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation." ACM Recommender Systems Challenge, 2018.
Using Deep Learning for Title-Based Semantic Subject Indexing to Reach Competitive Performance to Full-Text
Florian Mai, Lukas Galke, Ansgar Scherp, "Using Deep Learning for Title-Based Semantic Subject Indexing to Reach Competitive Performance to Full-Text." Joint Conference on Digital Libraries, 2018.
Multi Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels
Lukas Galke, Florian Mai, Iacopo Vagliano, Ansgar Scherp, "Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels." 26th Conference on User Modeling, Adaptation and Personalization, 2018.
A Case Study of Closed-Domain Response Suggestion with Limited Training Data
Lukas Galke, Gunnar Gerstenkorn, Ansgar Scherp, "A Case Study of Closed-Domain Response Suggestion with Limited Training Data." Database and Expert Systems Applications, 2018.
Can Graph Neural Networks Go Online? An Analysis of Pretraining and Inference
Lukas Galke, Iacopo Vagliano, Ansgar Scherp, "Can Graph Neural Networks Go `Online`? An Analysis of Pretraining and Inference." Representation Learning on Graphs and Manifolds, ICLR Workshop, 2019.
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
Florian Mai, Lukas Galke, Ansgar Scherp, "CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model." International Conference on Learning Representations, 2019.
Inductive Learning of Concept Representations from Library-Scale Corpora with Graph Convolution
Lukas Galke, Tetyana Melnychuk, Eva Seidlmayer, Steffen Trog, Konrad Foerstner, Carsten Schultz, Klaus Tochtermann, "Inductive Learning of Concept Representations from Library-Scale Corpora with Graph Convolution." INFORMATIK, 2019.
What If We Encoded Words as Matrices and Used Matrix Multiplication as Composition Function?
Lukas Galke, Florian Mai, Ansgar Scherp, "What If We Encoded Words as Matrices and Used Matrix Multiplication as Composition Function?." INFORMATIK, 2019.
Früherkennung wissenschaftlicher Konvergenz im Hochschulmanagement
Tetyana Melnychuk, Lukas Galke, Eva Seidlmayer, Konrad Förstner, Klaus Tochtermann, Carsten Schultz, "Früherkennung wissenschaftlicher Konvergenz im Hochschulmanagement." Hochschulmanagement, 2021.
Lifelong Learning of Graph Neural Networks for Open-World Node Classification
Lukas Galke, Benedikt Franke, Tobias Zielke, Ansgar Scherp, "Lifelong Learning of Graph Neural Networks for Open-World Node Classification." International Joint Conference on Neural Networks, 2021.
Emergent Communication for Understanding Human Language Evolution
Lukas Galke, Yoav Ram, Limor Raviv, "Lifelong Learning of Graph Neural Networks for Open-World Node Classification." Emergent Communication workshop at ICLR, 2021.
Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP
Lukas Galke, Ansgar Scherp, "Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP" ACL 2022.
Talks
Word Embeddings for Practical Information Retrieval
Conference proceedings talk at INFORMAITK 2017, Chemnitz, Germany
Reranking-based Recommender Systems with Deep Learning
Conference proceedings talk at INFORMATIK 2017, Chemnitz, Germany
Using Titles vs. Full-text as Source for Automated Semantic Document Annotation
Conference proceedings talk at K-CAP, Austin, Texas
Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels
Conference proceedings talk at Conference on User Modeling, Adaptation and Personalization, Singapore, Singapore
Using Titles vs. Full-text as Source for Automated Semantic Document Annotation
Conference proceedings poster presentation at ICLR, New Orleans, Lousiana
Can Graph Neural Networks Go Online? An Analysis of Pretraining and Inference
Workshop proceedings poster presentation at ICLR, New Orleans, Lousiana
What If We Encoded Words as Matrices and Used Matrix Multiplication as Composition Function?
Conference proceedings talk at INFORMATIK 2019, Kassel, Germany
Inductive Learning of Concept Representations from Library-Scale Corpora with Graph Convolution
Conference proceedings talk at INFORMATIK 2019, Kassel, Germany
Scaling Up Graph Neural Networks
Reading group talk at GNN Reading Group, online
Lifelong learning of graph neural networks for open-world node classification
Conference proceedings talk at International Joint Conference on Neural Networks, online
COVID-19++: A Citation-Aware Covid-19 Dataset for the Analysis of Research Dynamics
Workshop proceedings talk at 2021 IEEE International Conference on Big Data (Big Data), online
Emergent Communication for Understanding Human Language Evolution
Discussion Session at EmeCom workshop at ICLR'22, online
Teaching
Review activity
- Served as a reviewer for:
- Empirical Methods for Natural Language Processing (conference)
- SpringerNature Artificial Intelligence Review (journal)
- IEEE Transactions on Neural Networks and Learning Systems (journal, special issue)
- Graph Representation Learning Workshop at the International Conference on Machine Learning (workshop)
- Knowledge-based systems (journal)