In academic literature, maintenance scheduling optimisation is often seen as a type of resource-constrained project scheduling problem, a topic studied extensively since the late 1950s. However, existing mathematical models and solution methods, including exact, heuristic, and meta-heuristic approaches, are not fully suited for the unique challenges of real-world scheduling problems in the resources and energy industry, characterised by their large-scale and tight constraints.
In this presentation, Hoa will give a general picture on how researchers at the Optimisation Theme at ITTC are working to bridge these gaps and develop practical solutions for optimising maintenance schedules for our industry partners.
When - 1.30pm Friday 15 December 2023
Where - Microsoft Teams meeting
Join on your computer, mobile app or room device
Can we retrieve information from a structured database by asking questions like we ask ChatGPT? What are the technical building blocks necessary to enable a natural language interface to a structured database, be it relational or graph-based?
When you access and try understanding structured maintenance data, for example, a graph database, you might like to question this database using your everyday language. Using everyday language or what we call ‘natural language’ to question a database will not give you an accurate answer as it is not executable in a database.
Ziyu's presentation will take you through how she has developed a baseline using a technique called ‘Text-to-Cypher: A Baseline Natural Language Interface for Property Graph Databases’.
What is a Cypher query, you ask?
Well, Cypher is Neo4j's query language developed in 2011. It is one of NoSQL query languages. Neo4j tops the DB engine ranking of Graph DBMS (https://db-engines.com/en/ranking). Different storage and query paradigms have different characteristics, especially in terms of representation and query expressivity, and scalability. While SQL, which is the first database query language, comprises a sophisticated data structure and expressive query language, NoSQL trades schema and query expressivity for scalability. Her proposed baseline has enormous potential in the maintenance domain as it has been trained on her proposed parallel corpus which spans 155 domains.
Ziyu's work, called 'Text-to-Cypher', features two T5-style baseline models. T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks. The availability of such corpus and baselines can help develop and evaluate new transformer-based methods in understanding the text-to-NoSQL query language generation problem in order to support maintainers without any coding experience and domain knowledge to access structured database data in natural language.
Ziyu will present her work virtually next Friday 17 March 1.00pm Perth time or 3.00pm Brisbane time.
Location Microsoft Teams meeting
Join on your computer, mobile app or room device.
Meeting ID: 462 973 946 975