Related papers: Why Task-Based Training is Superior to Traditional…

All users of spreadsheets struggle with the problem of errors. Errors are thought to be prevalent in spreadsheets, and in some instances they have cost organizations millions of dollars. In a previous study of 50 operational spreadsheets we…

Despite several deficiencies, the use of spreadsheets in statistics courses is increasingly common. In this paper we discuss many shortcomings resulting from this approach. We suggest a technique integrating a spreadsheet and a dedicated…

Within the framework of Technological Pedagogical and Content Knowledge, subject integration is one possible solution for the introduction of meaningful digitalization and digitization in schools. This process incorporates that any school…

Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this paper, we identify one cause of overfitting related to current…

Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization algorithms have instead been proposed, inspired by various…

While scientists increasingly recognize the importance of metadata in describing their data, spreadsheets remain the preferred tool for supplying this information despite their limitations in ensuring compliance and quality. Various tools…

Recent studies show that task distribution plays a vital role in the meta-learner's performance. Conventional wisdom is that task diversity should improve the performance of meta-learning. In this work, we find evidence to the contrary; (i)…

In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in…

Business rules represent the knowledge that guides the operations of a business organization. They are implemented in software applications used by organizations, and the activity of extracting them from software is known as business rule…

Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task. However, little work has paid attention to how these models generalize to realistic unseen data, which naturally raises a question: does this…

This paper presents the findings of a case study of spreadsheet use in a higher education institution in the UK. The paper considers the use of spreadsheets in two units of the organisation, academic registry and finance. Spreadsheet use is…

Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In…

This paper presents the authors recommended practices for spreadsheet testing. Documented spreadsheet error rates are unacceptable in corporations today. Although improvements are needed throughout the systems development life cycle,…

In multi-task learning several related tasks are considered simultaneously, with the hope that by an appropriate sharing of information across tasks, each task may benefit from the others. In the context of learning linear functions for…

In this paper, we report some on-going focused research, but are further keen to set it in the context of a proposed bigger picture, as follows. There is a certain depressing pattern about the attitude of industry to spreadsheet error…

To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones (easy-to-hard generalization), or using unsupervised…

This paper presents a taxonomy for analytical spreadsheet models. It considers both the use case that a spreadsheet is meant to serve, and the engineering resources devoted to its development. We extend a previous three-type taxonomy, to…

Instruction tuning has been attracting much attention to achieve generalization ability across a wide variety of tasks. Although various types of instructions have been manually created for instruction tuning, it is still unclear what kind…

Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples…

In this paper, we explore the capability of an agent to construct a logical sequence of action steps, thereby assembling a strategic procedural plan. This plan is crucial for navigating from an initial visual observation to a target visual…