Julia Ive

Research Fellow

Dr. Julia Ive is a Research Fellow at the Data Science Institute at Imperial College London. Julia is also Head of NLP Research at Pangaea Data. She holds a PhD in Machine Translation from LIMSI-CNRS (France). Recently she has been mainly working on text generation problems, multimodality and classification in general and within the clinical domain. Julia has recently successfully led the EPSRC Healtex project pilot on creating privacy-safe artificial medical records to be used in research.

download cv j.ive[at]imperial.ac.uk

News/
Upcoming Activities.
News/Upcoming Activities.

  • 2013-2017

    PhD in Computer Science, LIMSI-CNRS, France and Cochrane France

    Advisors: Prof. François Yvon, Associate Prof. Aurélien Max

Experience.

  • Oct.2020-present

    PhD in Computer Science, LIMSI-CNRS, France and Cochrane France

    Managed by Prof. Yike Guo

  • Dec.2019-Oct.2020

    Imperial College London, Department of Computing, Research Associate in Multimodal Machine Learning

    Managed by Prof. Lucia Specia

  • Nov.2018-Dec.2019

    University of Sheffield, Department of Computer Science, Research Associate in Quality Estimation for Machine Translation

    Managed by Prof. Lucia Specia

  • Dec.2017-Nov.2018

    King’s College London, Institute of Psychiatry, Psychology & Neuroscience, Research Associate for Biomedical Natural Language Processing

    Managed by Prof. Robert Stewart

Education.

  • 2013-2017

    PhD in Computer Science, LIMSI-CNRS, France and Cochrane France

    Advisors: Prof. François Yvon, Associate Prof. Aurélien Max

Research Grants.

  • 2018-2019

    EPSRC Healtex Award, Towards shareable data in clinical NLP: Generating synthetic electronic health records

Organisation of Events.

  • Nov.2019

    Workshop on Medical Text Generation, Creating artificial medical records from real ones: are they safe for research?

    King's College London

Projects.

DeepQuest -- Framework for neural-based Quality Estimation

Developed at the University of Sheffield, DeepQuest provides state-of-the-art models for multi-level Quality Estimation.

Predicting Machine Translation (MT) quality can help in many practical tasks such as MT post-editing. The performance of Quality Estimation (QE) methods has drastically improved recently with the introduction of neural approaches to the problem. However, thus far neural approaches have only been designed for word and sentence-level prediction. We present a neural framework that is able to accommodate neural QE approaches at these fine-grained levels and generalize them to the level of documents. We test the framework with two sentence-level neural QE approaches: a state of the art approach that requires extensive pre-training, and a new light-weight approach that we propose, which employs basic encoders. Our approach is significantly faster and yields performance improvements for a range of document-level quality estimation tasks. To our knowledge, this is the first neural architecture for document-level QE. In addition, for the first time we apply QE models to the output of both statistical and neural MT systems for a series of European languages and highlight the new challenges resulting from the use of neural MT.

DeepQuest -- Framework for neural-based Quality Estimation

CopyCat

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit.

Investigation of rabbit’s neuronal reaction What is the main factor of peoples agression?

MMT-Delib

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit.

Investigation of rabbit’s neuronal reaction What is the main factor of peoples agression?

Publications.

Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation.

EACL (to Appear), 2021

Ive, J., Li, A.M., Miao, Y., Caglayan, O., Madhyastha, P., Specia, L.

Exploring Supervised and Unsupervised Rewards in Reinforcement Learning for Machine Translation.

EACL (to Appear), 2021

Ive, J., Wang, Z., Fomicheva, M., Specia, L.

Generation and evaluation of artificial mental health records for Natural Language Processing.

Npj Digital Medicine, 2020

Ive, J. et al.

Exploring Transformer Text Generation for Medical Dataset Augmentation.

LREC, 2020

Amin-Nejad, A., Ive, J., & Velupillai, S.

Deep copycat networks for text-to-text generation.

EMNLP-IJCNLP, 2020

Ive, J., Madhyastha, P., & Specia, L.

Is artificial data useful for biomedical Natural Language Processing algorithms?

BioNLP Workshop, 2019

Wang, Z., Ive, J., Velupillai, S., & Specia, L.

Distilling translations with visual awareness.

ACL, 2019

Ive, J., Madhyastha, P., & Specia, L.

Hierarchical neural model with attention mechanisms for the classification of social media text related to mental health.

Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic, 2018

Ive, J., Gkotsis, G., Dutta, R., Stewart, R., & Velupillai, S.