Analyzing Text Representations under Tight Annotation Budgets: Measuring Structural Alignment
Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation budgets the choice of data representation is key. The goal of this paper is to better understand why this is so. With this goal in mind, we propose a metric that measures the extent to which a given representation is structurally aligned with a task. We conduct experiments on several text classification datasets testing a variety of models and representations. Using our proposed metric we show that an efficient representation for a task (i.e. one that enables learning from few samples) is a representation that induces a good alignment between latent input structure and class structure.
Code (0)
등록된 구현이 없습니다.
Tasks
text-classificationText ClassificationSimilar Papers 제목 키워드 기반
Analyzing structural characteristics of object category representations from their semantic-part distributions
Studies from neuroscience show that part-mapping computations are employed by human visual system in the process of object recognition. In this work, we present an approach for analyzing semantic-part characteristics of …
ObjectObject RecognitionBoosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations
While Multimodal Large Language Models (MLLMs) have achieved remarkable success in 2D visual understanding, their ability to reason about 3D space remains limited. To address this gap, we introduce geometrically referenc…
Mathematical ReasoningSpatial ReasoningexBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models
Large Transformer-based language models can route and reshape complex information via their multi-headed attention mechanism. Although the attention never receives explicit supervision, it can exhibit recognizable patter…
DiversityJaMIE: A Pipeline Japanese Medical Information Extraction System with Novel Relation Annotation
In the field of Japanese medical information extraction, few analyzing tools are available and relation extraction is still an under-explored topic. In this paper, we first propose a novel relation annotation schema for …
RelationRelation ExtractionAn Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE
Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid. Identifying insights helps analysts understand the collaboration of various parts of the gr…