About the Project
While Question Answering (QA) systems have a long tradition in the field of Natural Language Processing (NLP), the associated problems of defining explainability in the context of QA, developing methods which have explanations as first-class citizens and building the supporting evaluation frameworks, are still largely unsolved. The demand for explainability in the context of QA is aggravated by the fact that while Deep Learning methods delivered improvements in accuracy for QA, the pathway for QA towards real world applications would still require full explainability.
This project focuses its contributions on the investigation of explainable neuro-symbolic models for QA and Dialogue Systems. While state-of-the-art QA uses end-to-end Deep Learning models, which are predominantly black-box models (i.e. not explainable) and require large sets of annotated data (high portability costs), the methods which will be explored in the context of this project will use large-scale knowledge graphs, ontologies, automated reasoning, and neuro-symbolic ML methods.
Entry Requirements:
Applications should be submitted online and candidates should make direct contact with the Manchester supervisor to discuss their application directly. Applicants must have obtained, or be about to obtain, at least an upper second class honours degree (or equivalent) in a relevant subject.
Funding Notes
This project is available to UK/EU candidates. Funding covers fees (UK/EU rate) and stipend for four years. Overseas candidates can apply providing they can pay the difference in fees and are from an eligible country. Candidates will be required to split their time between Manchester and Singapore, as outlined on www.manchester.ac.uk/singaporeastar.
As an equal opportunities institution we welcome applicants from all sections of the community regardless of gender, ethnicity, disability, sexual orientation and transgender status. All appointments are made on merit.
References
Vivian S. Silva, André Freitas, Siegfried Handschuh, Recognizing and Justifying Text Entailment through Distributional Navigation on Definition Graphs, Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), New Orleans, USA, 2018
Matthias Cetto, Christina Niklaus, André Freitas and Siegfried Handschuh, Creating a Hierarchy of Semantically-Linked Propositions in Open Information Extraction, In Proceedings of the 27th International Conference on Computational Linguistics (COLING), New-Mexico, USA, 2018.
André Freitas, Edward Curry, Natural Language Queries over Heterogeneous Linked Data Graphs: A Distributional-Compositional Semantics Approach, In Proceedings of the 19th International Conference on Intelligent User Interfaces (IUI), Haifa, 2014.
X Han, J Kim, CK Kwoh. Active learning for ontological event extraction incorporating named entity recognition and unknown word handling. Journal of biomedical semantics 7 (1), 22, 2016.
Y Ma, J Kim, B Bigot, TM Khan. Feature-enriched word embeddings for named entity recognition in open-domain conversations. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016.
Continue with Facebook
