paper-with-me

홈 › Papers

Analyzing Text Representations under Tight Annotation Budgets: Measuring Structural Alignment

2022-10-11 · César González-Gutiérrez, Audi Primadhanty, Francesco Cazzaro, Ariadna Quattoni

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.

📄 PDF Abstract BibTeX arXiv:2210.05721

Code (0)

등록된 구현이 없습니다.

Tasks

text-classificationText Classification

Similar Papers 제목 키워드 기반

Analyzing structural characteristics of object category representations from their semantic-part distributions

2015-09-15 · Ravi Kiran Sarvadevabhatla, Venkatesh Babu R

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 Recognition

Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations

2026-03-09 · Jiangye Yuan, Gowri Kumar, Baoyuan Wang arxiv

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 Reasoning

exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models

2020-07-01 · ACL 2020 6 · Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann

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…

Diversity

JaMIE: A Pipeline Japanese Medical Information Extraction System with Novel Relation Annotation

2022-06-01 · LREC 2022 6 · Fei Cheng, Shuntaro Yada, Ribeka Tanaka, Eiji Aramaki 외

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 Extraction

An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE

2019-05-22 · Tianye Zhang, Haozhe Feng, Zexian Chen, Can Wang 외

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…