PhD Studentship: Large Language Models for Habitat and Environmental Impact Event Extraction with Location Refinement

PhD Supervisor: Stuart Middleton

Supervisory Team: Stuart Middleton, Christine Evers

Project description:

Monitoring risks to natural habitats is a critical element for protecting and sustaining biodiversity. Pollution, wildfire, flooding, appearance of invasive species and other habitat changing events are highly localized and difficult to monitor manually. Often an event is observed well after damage to biodiversity has been done. Social media and Natural Language Processing offers opportunities to use AI to 24/7 review localized public posts from concerned citizens and volunteer environmentalists.

This PhD will explore event extraction using deep-learning based Large Language Models (LLMs) for social media posts about instances of habitat and environmental impact. Posts will be text-based (posted text + metadata) but will importantly include links to associated media content such as images and videos of mentioned locations and impact. Relation-Aware Prototyping [Meng 2023] will be coupled with ideas from work on LLM augmentation using OpenStreetMap [Manvi 2023] to provide a novel Information Extraction model that supports prototyping with hyper-local location refinement of events and event context. To reduce environmental impact of GPU-use for LLM training parameter-reduction methods such a QLoRA will be employed from the start.

The project will have an opportunity to engage with Kew Gardens as a potential bio-diversity end user partner.

[Meng 2023] RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction https://aclanthology.org/2023.emnlp-main.316/

[Manvi 2023] GeoLLM: Extracting Geospatial Knowledge from Large Language Models https://openreview.net/forum?id=TqL2xBwXP3

This is a fully funded 4-year integrated PhD (iPhD) programme and is part of the UKRI AI Centre for Doctoral Training in AI for Sustainability (SustAI). For more information about SustAI, please see: https://sustai.info/

You will join the School of Electronics and Computer Science within the University of Southampton, ranked top 1% of universities worldwide. We will support the development of your future career and give you opportunities including teaching assistantships, professional networking via leading organizations such as Alan Turing Institute, £31M RAI UK Hub, and access to Future Worlds to explore commercialization of your research.

If you wish to discuss any details of the project informally, please contact Professor Enrico Gerding, Director of the SustAI CDT, Email: sustai@soton.ac.uk.

Entry Requirements

A very good undergraduate degree (at least a UK 2:1 honours degree, or its international equivalent).

Closing date: 8 April 2024.

Applications will be considered in the order that they are received, the position will be considered filled when a suitable candidate has been identified.

Funding: We offer a range of funding opportunities for both UK and international students, including Bursaries and Scholarships.  For more information please visit PhD Scholarships | Doctoral College | University of Southampton  Funding will be awarded on a rolling basis, so apply early for the best opportunity to be considered.

How To Apply

Apply online by clicking the 'Apply' button, above.

Select programme type (Research), 2024/25, Faculty of Engineering and Physical Sciences, next page select “PhD iPhD AI for Sustainability (Full time)”. In Section 2 of the application form you should insert the name of the supervisor.

Applications should include:

• Research Proposal
• Curriculum Vitae
• Two reference letters
• Degree Transcripts/Certificates to date

For further information please contact: feps-pgr-apply@soton.ac.uk

Advert information