My research focuses on various aspects of data-driven approaches to natural language processing, with a particular interest in multimodal and multilingual context models and work at the intersection of language and vision. My work has various applications such as machine translation, image captioning, quality estimation and text adaptation.
I currently hold an ERC (European Research Council) Starting Grant on Multi-modal Context Modelling for Machine Translation.
I am also part-time Professor of Language Engineering at the University of Sheffield. Check my Sheffield page for more.
Madhyastha P, Wang J, Specia L, 2018, The role of image representations in vision to language tasks, Natural Language Engineering, Vol:24, ISSN:1351-3249, Pages:415-439
et al., 2019, Probing the need for visual context in multimodal machine translation, Conference of the North American Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Pages:4159-4170
Pranava M, Josiah W, Specia L, VIFIDEL: Evaluating the Visual Fidelity of Image Descriptions, Conference of the Association for Computational Linguistics
Ive J, Madhyastha P, Specia L, Distilling Translations with Visual Awareness, Conference of the Association for Computational Linguistics