Question Answering for Testing in Industrial Contexts at Queen’s University Belfast on FindAPhD.com

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities

Dr Hui Wang, Prof Karen Rafferty No more applications being accepted Competition Funded PhD Project (Students Worldwide)

Belfast United Kingdom Electrical Engineering Electronic Engineering Computer Science

About the Project

Project Introduction:

This proposed research aligns to the new Advanced Research and Engineering centre (ARC) within Northern Ireland. This Centre will drive future innovations in technology and enhance our capabilities in important research areas such as robotic process automation (RPA), workflow automation, visualisation, data analytics and artificial intelligence (AI). The Centre brings together expertise from PwC, University of Ulster and Queen’s University Belfast.

This research project aligns to the workflow and AI streams within the Centre. A selection process will determine the strongest candidates across a range of projects, who may then be offered funding for their chosen project. Approximately £6000 per year is payable to the sponsored student in addition to the normal stipend.

The automation of repetitive information processing tasks has the potential to realise enormous advances in productivity and user satisfaction across a range of business services and solutions. Deep learning approaches, using large scale neural network models, have recently been successfully applied to many information processing tasks, including knowledge discovery and information extraction, text summarization, and text generation. Such methods have been used to generate powerful models in the legal and commercial domain; for example, state-of-the-art Natural Language Processing models have been applied to the analysis and summarization of legal documents (Elwany et al 2019), legal textual entailment (Rosa et al 2021; Yoshioka et al 2021) and modelling the structure of commercial contracts (Hegel et al 2021). Moreover, document image understanding models have shown promising utility in extracting relevant information from structured commercial documents. The time is therefore ripe to develop and build systems that automate textual data analysis and text generation tasks for a range of real-world, commercially orientated problems.

Project Summary:

This PhD project will investigate automatic question/answer generation from text using deep learning techniques, and the use of question answering for testing in education and/or industrial contexts.

Project Description: Question answering is part of how we learn. We learn by asking questions and searching for correct answers, and by explaining the correct and incorrect answers. Question answering is also an important means of testing learning attainment. Teachers set questions and students answer them to evidence attainment. Question answering is also an important means of testing compliance with regulations (rules and laws) in industry. Employees are often asked to complete courses about regulations and to evidence compliance by completing some tests. In either of these cases, we typically need to set questions and their correct answers manually, which is time consuming; furthermore, question answering is done by humans.

In this PhD project, we will build on existing work on question-answer generation [1] and natural language processing in the School to go a big step further – generating questions and their answers (e.g., in the form of question-answer pairs) from text automatically, and performing automatic testing based on user submitted documents. We will also evaluate through a case study in an industrial context. Generating high-quality question-answer pairs is a key part of this project and provides the basis for automatic testing. In general question-answer pair generation will improve the performance of question answering systems, help acquire knowledge from text, and promote machine reading comprehension.

Objectives:

Investigate automatic question-answer pair generation based on deep learning and knowledge graph
Investigate automatic testing based on question-answer pairs and user submitted documents
Conduct a case study in an industrial context.

Full-Time

Start Date: 01/10/2023

Application Closing date: 28/2/23

Funding Notes

International: We welcome applications from international candidates. For candidates who do not meet the DfE funding residency requirements, a small number of international studentships may be available from the School. These are awarded via a competitive, selection process which will determine the strongest candidates across a range of School projects, who may then be offered funding for their chosen project.

UK/ROI: Applications from candidates in the UK and ROI are eligible for consideration for a DfE Studentship. As this is an industry-sponsored PhD, approximately £6,000 per year is payable to the sponsored student in addition to the annual DfE stipend if successful. Full eligibility information for UK/ROI candidates can be viewed via: View Website

Academic Requirements:

A 1st or 2.1 Hons degree or MSc with distinction in Electrical/Electronic Engineering or Computer Science with relevant technological experience.

To Apply please complete an application through the Direct Applications Portal: https://dap.qub.ac.uk/portal/user/u_login.php

References

[1] Zhengrong Guo, Gongde Guo, Hui Wang (2022. Question-answer pair generation method based on key-phrase extraction and answer filtering. Under review.
[2] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
[3] Elwany, E., Moore, D., & Oberoi, G. (2019). Bert goes to law school: Quantifying the competitive advantage of access to large legal corpora in contract understanding. arXiv preprint arXiv:1911.00473.
[4] Hegel, A., Shah, M., Peaslee, G., Roof, B., & Elwany, E. (2021). The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues. arXiv preprint arXiv:2107.08128.
[5] Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., ... & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
[6] Ormerod, M., Martínez-del-Rincón, J., Robertson, N., McGuinness, B., & Devereux, B. (2019, August). Analysing representations of memory impairment in a clinical notes classification model. In Proceedings of the 18th BioNLP Workshop and Shared Task (pp. 48-57).
[7] Rogers, A., Kovaleva, O., & Rumshisky, A. (2020). A primer in bertology: What we know about how bert works. Transactions of the Association for Computational Linguistics, 8, 842-866.
[8] Rosa, G. M., Rodrigues, R. C., de Alencar Lotufo, R., & Nogueira, R. (2021, June). To tune or not to tune? zero-shot models for legal case entailment. In Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law (pp. 295-300).
[9] Yoshioka, M., Aoki, Y., & Suzuki, Y. (2021, June). BERT-based ensemble methods with data augmentation for legal textual entailment in COLIEE statute law task. In Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law (pp. 278-284).

We’ve won a FindAMasters and FindAPhD Postgrad Award!

As a previous winner of a Postgrad Award, our university community has been recognised for their excellence in, and dedication to, postgraduate education. Studying with us means you’ll be part of a supportive environment that has been celebrated for its achievements and positive impact on our postgraduate students.

Find out more