Research
Research interests
My current research focuses on NLP and its many real-life applications (ranging from text mining to machine translation and dialogue systems) and on the development of responsible and human-centric NLP / AI aimed at social and global good.
Some current areas of interest include:
human-centric NLP
interpretability, explainability, fairness and trustworthiness of NLP
low resource NLP
multilingual NLP
dialogue systems and conversational AI
domain, task and language adaptation / transfer
information extraction, text mining, knowledge discovery
machine learning / deep learning
NLP for data science (e.g., biomedical and cognitive sciences)
NLP for health
real-world and responsible applications of NLP
Some of my current and past projects
Towards Globally Equitable Language Technologies. ERC Advanced / UKRI Frontier Grant (2023-2028)
Advancing cross-lingual transfer for conversational AI (2021-2023)
MultiConvAI - Enabling Multilingual Conversational AI. Funded by ERC (2021-2022).
Modeling Idiomaticity in Human and Artificial Language Processing. Funded by EPSRC (2020-2024).
Building Multilingual Multi-Domain Dialogue Systems (2019-2023).
ESG RoboFactory. Funded by Innovate UK (2020-2022).
Automatic Induction and Adaptation of Syntactic Structures for Improved Cross-Lingual NLP. Google Faculty Award (2019-2020).
LEXICAL - Lexical Acquisition across Languages. Funded by ERC (2015-2021).
EF Education First Research Lab for Applied Language Learning. Funded by Education First (2015-2020).
LION - Literature-based discovery for cancer biology. Funded by MRC (2015-2018)
PheneBank - automatic extraction and validation of a database of human phenotype-disease associations from the scientific literature. Funded by MRC (2015-2018)
ENRICH - Enriched phrasal representations for improved language understanding. Google Faculty Award (2015-2016)
The Education First-Cambridge Learner Corpus of English - a data driven approach to second language learning. Funded by EF and Isaac Newton Trust (2010-2015).
Developing Lexical Resources for Natural Language Processing Applications. University Research Fellowship. Funded by the Royal Society (2005-2014).
PANACEA - Platform for Automatic, Normalized Annotation and Cost-Effective Acquisition of Language Resources for Human Language Technologies. Funded by EU FP7 (2010-2012).
Lexical Acquisition for the Biomedical Domain. Funded by EPSRC (2009-2012).
Developing Multilingual Technologies for Automatic Lexical Acquisition. Funded by Isaac Newton Trust (2010-2012).
CRAB - Using Text Mining to Aid Cancer Risk Assessment. Funded by MRC, EU and FSA and FORMAS in Sweden (2008).
COMPLEX - Computational Natural Language Processing and the Neuro-Cognition of Language. Co-funded by EPSRC, ESRC and MRC (2008-2011).
Developing Multilingual Technologies for Automatic Lexical Acquisition. Funded by British Council (2008-2009).
ACLEX - Accurate and Comprehensive Lexical Classification for Natural Language Processing Applications. Funded by EPSRC (2005-2008).
Using Automatic Verb Classification to Aid Event Extraction. JSPS Postdoctoral Fellowship. Funded by the Japan Society for the Promotion of Science (2004-2005)