Heriot-Watt University Featured PhD Programmes
Imperial College London Featured PhD Programmes
King’s College London Featured PhD Programmes
University of Kent Featured PhD Programmes
University of Bristol Featured PhD Programmes

Semantic Reading


Project Description

In the last decade, Natural Language Processing has seen impressive improvements in tasks such as question answering and text summarization. These tasks require some "understanding" of the meaning of text which, in turn, involves identifying and interpreting semantic relationships between pieces of text. The latter is based on knowledge bases and linguistic resources such as WordNet that provide very broad coverage for a large number of terms, but with only a limited number of relations.

In this project, we will develop an approach for these tasks that is based on a tighter integration of the NLP tools, in particular its Neural Network-based machine learning models, with rich OWL ontologies. Suitable OWL ontologies exist for a range of application domains and often cover a wide range of terms and relationships between these. The aim of this integration is to investigate in how far this integration can improve the performance of these tasks, in particular make the approach "background-knowledge-able" and thus explainable. The project will focus on adapting and extending existing KB-driven neuro-symbolic architectures such as TensorLog, Distributional Navigational Models, Logical Tensor Networks, Deep Reinforcement Learning to benefit from the accuracy provided by reasoning over high-quality ontologies.

References

Vivian Dos Santos Silva, Siegfried Handschuh, Andr?? Freitas: Recognizing and Justifying Text Entailment Through Distributional Navigation on Definition Graphs. AAAI 2018: 4913-4920
https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16246

Viachaslau Sazonau, Uli Sattler: Mining Hypotheses from Data in OWL: Advanced Evaluation and Complete Construction. International Semantic Web Conference (1) 2017: 577-593
https://doi.org/10.1007/978-3-319-68288-4_34

Related Subjects

How good is research at University of Manchester in Computer Science and Informatics?

FTE Category A staff submitted: 44.86

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2019
All rights reserved.