World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
50
Citations
20094
World Ranking
5478
National Ranking
329

Overview

Ivan Titov is affiliated with the University of Edinburgh in the United Kingdom. Their research is primarily situated within the broad field of Computer Science, with a strong emphasis on Artificial Intelligence. They have also contributed to related subfields including Computer Vision and Pattern Recognition, Electronic, Optical and Magnetic Materials, Molecular Biology, and Mechanical Engineering.

The main areas of scientific inquiry for Ivan Titov cover several topics, including:

  • Topic Modeling
  • Natural Language Processing Techniques
  • Multimodal Machine Learning Applications
  • Domain Adaptation and Few-Shot Learning
  • Magnetic Properties of Alloys
  • Explainable Artificial Intelligence (XAI)
  • Magnetic Properties and Applications

Ivan Titov's publication record shows contributions to several frequently used venues across their academic career. The most prominent publication outlets include:

  • arXiv (Cornell University)
  • Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
  • Zurich Open Repository and Archive (University of Zurich)
  • Physical review. B./Physical review. B
  • Journal of Applied Crystallography

Notable recent papers authored or co-authored by Ivan Titov illustrate the breadth of their research and focus areas. These include:

  • "Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation," 2020, arXiv (Cornell University)
  • "Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking," 2020, arXiv (Cornell University)
  • "Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation," 2022, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
  • "Highly Parallel Autoregressive Entity Linking with Discriminative Correction," 2021, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Ivan Titov has collaborated frequently with several co-authors, reflecting sustained research partnerships. These co-authors include:

  • Rico Sennrich
  • Andreas Michels
  • Nicola De Cao
  • Wilker Aziz
  • Mirella Lapata

Their body of work contributes to advancements in neural machine translation, graph neural networks interpretation in NLP contexts, and entity linking methods. Across these domains, Ivan Titov's publications show an interdisciplinary link between computational linguistics, machine learning techniques, and applications involving multimodal datasets and magnetic material properties.

Best Publications

  • Modeling Relational Data with Graph Convolutional Networks

    Michael Sejr Schlichtkrull;Thomas N. Kipf;Peter Bloem;Rianne van den Berg

  • 5th International Conference on Learning Representations (ICLR 17)

    Serhii Havrylov;Ivan Titov

  • Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

    Elena Voita;Elena Voita;David Talbot;Fedor Moiseev;Fedor Moiseev;Rico Sennrich

  • Modeling online reviews with multi-grain topic models

    Ivan Titov;Ryan McDonald

  • Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

    Diego Marcheggiani;Ivan Titov

  • A Joint Model of Text and Aspect Ratings for Sentiment Summarization

    Ivan Titov;Ryan McDonald

  • Graph Convolutional Encoders for Syntax-aware Neural Machine Translation

    Jasmijn Bastings;Ivan Titov;Wilker Aziz;Diego Marcheggiani

  • Translating Video Content to Natural Language Descriptions

    Marcus Rohrbach;Wei Qiu;Ivan Titov;Stefan Thater

  • Inducing Crosslingual Distributed Representations of Words

    Alexandre Klementiev;Ivan Titov;Binod Bhattarai

  • Context-Aware Neural Machine Translation Learns Anaphora Resolution

    Elena Voita;Elena Voita;Pavel Serdyukov;Rico Sennrich;Rico Sennrich;Ivan Titov;Ivan Titov

  • Question Answering by Reasoning Across Documents with Graph Convolutional Networks

    Nicola De Cao;Wilker Aziz;Ivan Titov

  • Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

    Biao Zhang;Philip Williams;Ivan Titov;Rico Sennrich

  • A Latent Variable Model for Generative Dependency Parsing

    Ivan Titov;James Henderson

  • Interpretable Neural Predictions with Differentiable Binary Variables

    Jasmijn Bastings;Wilker Aziz;Ivan Titov

  • Improving Entity Linking by Modeling Latent Relations between Mentions

    Phong Le;Ivan Titov

  • Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols.

    Serhii Havrylov;Ivan Titov

  • Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks

    Diego Marcheggiani;Jasmijn Bastings;Ivan Titov

  • When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion

    Elena Voita;Elena Voita;Rico Sennrich;Ivan Titov

  • Information-Theoretic Probing with Minimum Description Length

    Elena Voita;Ivan Titov

  • The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives

    Elena Voita;Elena Voita;Rico Sennrich;Ivan Titov

Frequent Co-Authors

Rico Sennrich
Rico Sennrich University of Zurich
Mirella Lapata
Mirella Lapata University of Edinburgh
Barry Haddow
Barry Haddow University of Edinburgh
Max Welling
Max Welling University of Amsterdam
Dan Roth
Dan Roth University of Pennsylvania
Pavel Serdyukov
Pavel Serdyukov Yandex (Russia)
Gertjan van Noord
Gertjan van Noord University of Groningen
Bernt Schiele
Bernt Schiele Max Planck Institute for Informatics
Yang Liu
Yang Liu Microsoft Research Asia (China)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring an online degree in Computer Science opens doors to a variety of related programs that build versatile, high-demand skills. If you have a passion for theoretical and applied science, an online bachelor's degree in physics can strengthen your problem-solving and analytical abilities—qualities highly valued in tech industries.

For those interested in data, pursuing a data scientist degree is a powerful way to specialize in fields such as machine learning, AI, and analytics. These qualifications can lead to some of the most rewarding and fast-growing careers in technology.

Another popular pathway is an online bachelor’s in electrical engineering. This degree pairs well with Computer Science and offers opportunities in fields like robotics, embedded systems, and hardware design.

If you’re seeking a quicker route to boost your employability or complement your studies, consider looking into easy certifications to get. Many of these certifications require less time than a full degree but can significantly increase your earning potential and career prospects.

Best Scientists Citing Ivan Titov

Trending Scientists