Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size
In this paper, we experiment with a recently proposed visual reasoning task dealing with quantities {--} modeling the multimodal, contextually-dependent meaning of size adjectives ({}big{'}, {}small{'}) {--} and explore the impact of varying the training data on the learning behavior of a state-of-art system. In previous work, models have been shown to fail in generalizing to unseen adjective-noun combinations. Here, we investigate whether, and to what extent, seeing some of these cases during training helps a model understand the rule subtending the task, i.e., that being big implies being not small, and vice versa. We show that relatively few examples are enough to understand this relationship, and that developing a specific, mutually exclusive representation of size adjectives is beneficial to the task.
Code (0)
등록된 구현이 없습니다.
Tasks
Small Data Image ClassificationVisual ReasoningSimilar Papers 제목 키워드 기반
Bayes' Power for Explaining In-Context Learning Generalizations
Traditionally, neural network training has been primarily viewed as an approximation of maximum likelihood estimation (MLE). This interpretation originated in a time when training for multiple epochs on small datasets wa…
In-Context LearningAssessing the role of small farmers and households in agriculture and the rural economy and measures to support their sustainable development
The Ministry of Economy has an interest and demand in exploring how to increase the set of [legally registered] small family farmers in Ukraine and to examine more in details measures that could reduce the scale of the s…
Exploring AI Futures Through Role Play
We present an innovative methodology for studying and teaching the impacts of AI through a role play game. The game serves two primary purposes: 1) training AI developers and AI policy professionals to reflect on and pre…
Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established tha…
Multi-Task LearningRepresentation LearningEnvironmental engineering is an emergent feature of diverse ecosystems and drives community structure
A central question in ecology is to understand the ecological processes that shape community structure. Niche-based theories have emphasized the important role played by competition for maintaining species diversity. Man…