Teaching

Publications

Software

Collaborators


CV (PDF)

Bio

Ivan Titov Иван Титов

Reader (≈ US Associate Prof)
Insitute for Language, Cognition and Computation, School of Informatics
University of Edinburgh, UK

UHD (≈ US Associate Prof), part-time
Institute for Logic, Language and Computation, FNWI
University of Amsterdam, Netherlands

Office: IF 3.28
E-mail: ititov (at) inf.ed.ac.uk
Phone: +44 131 6513092

I am an associate professor (Reader) in the Institute for Language, Cognition and Computation (ILCC) at the School of Informatics of the University of Edinburgh. I am also a part-time faculty at the Institute of Logic, Language and Computation of the University of Amsterdam. My research interests are in natural language processing (incl. semantics and syntax) and machine learning.

My research is supported by personal grants (ERC Starting grant and NWO VIDI), as well as industrial funding / collaborations (incl. Google, SAP and Yandex).

I am an action editor for the journal of machine learning research (JMLR), Transactions of ACL (TACL), a member of editorial board of JAIR, an advisory board member for European Chapter of ACL. My other professional services include being a PC co-chair for *SEM 2016 and CoNLL 2018, a senior area chair for ACL 2019, an area chair for at ACL 2016, EMNLP 2014, EACL 2012, ICLR 2017 and 2019 and NIPS 2017, a senior PC member for IJCAI 2011. I will be program co-chair for ICLR 2021.


Team


Recent publications   (Full list) (Google Scholar)

2019

  • The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives
    Elena Voita, Rico Sennrich and Ivan Titov
    EMNLP 2019.
    abstract   bib   paper    code blog
  • Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks
    Xinchi Chen, Chunchuan Lyu and Ivan Titov
    EMNLP 2019.
    abstract   bib   paper   
  • Context-Aware Monolingual Repair for Neural Machine Translation
    Elena Voita, Rico Sennrich and Ivan Titov
    EMNLP 2019.
    abstract   bib   code blog paper   
  • Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs
    Bailin Wang, Ivan Titov and Mirella Lapata
    EMNLP 2019.
    abstract   bib   paper   
  • Semantic Role Labeling with Iterative Structure Refinement
    Chunchuan Lyu, Shay B. Cohen and Ivan Titov
    EMNLP 2019.
    abstract   bib   paper   
  • Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention
    Biao Zhang, Ivan Titov and Rico Sennrich
    EMNLP 2019.
    abstract   bib   paper   
  • Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts
    Denis Emelin, Ivan Titov and Rico Sennrich
    WMT 2019.
    abstract   bib   paper   
  • Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
    Elena Voita, David Talbot, Fedor Moiseev, Rico Sennrich and Ivan Titov
    ACL 2019.
    abstract   bib   paper    code blog
  • Interpretable Neural Predictions with Differentiable Binary Variables
    Jasmijn Bastings, Wilker Aziz and Ivan Titov
    ACL 2019.
    abstract   bib   paper    code
  • Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming
    Caio Corro and Ivan Titov
    ACL 2019.
    abstract   bib   paper    code
  • Distant Learning for Entity Linking with Automatic Noise Detection
    Phong Le and Ivan Titov
    ACL 2019.
    abstract   bib   paper    code
  • Boosting Entity Linking Performance by Leveraging Unlabeled Documents
    Phong Le and Ivan Titov
    ACL 2019.
    abstract   bib   paper    code
  • When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion
    Elena Voita, Rico Sennrich and Ivan Titov
    ACL 2019.
    abstract   bib   paper    code and test sets
  • Block Neural Autoregressive Flow
    Nicola De Cao, Wilker Aziz and Ivan Titov
    UAI 2019.
    abstract   bib   paper    code
  • Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder
    Caio Corro and Ivan Titov
    ICLR 2019.
    abstract   bib   paper    code
  • Question Answering by Reasoning Across Documents with Graph Convolutional Networks
    Nicola De Cao, Wilker Aziz and Ivan Titov
    NAACL 2019.
    abstract   bib   paper   
  • Single Document Summarization as Tree Induction
    Yang Liu, Ivan Titov and Mirella Lapata
    NAACL 2019.
    abstract   bib   paper    code

2018

  • Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks
    Diego Marcheggiani, Jasmijn Bastings and Ivan Titov
    NAACL 2018.
    abstract   bib   paper
  • Modeling Relational Data with Graph Convolutional Networks
    Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov and Max Welling
    ESWC 2018 (best student paper award).
    abstract   bib   paper
  • Embedding Words as Distributions with a Bayesian Skip-gram Model
    Arthur Brazinskas, Serhii Havrylov and Ivan Titov
    COLING 2018.
    abstract   bib   paper
    A earlier version appeared at NIPS Bayesian deep learning workshop

For a long list of papers (incl. pre-2018 articles) follow this link.


Recent teaching (Full list)


Previous Affiliations / Education