A Large-Scale Sensitivity Analysis on Latent Embeddings and Dimensionality Reductions for Text Spatializations

• URL: http://arxiv.org/abs/2407.17876v1
• Date: Thu, 25 Jul 2024 08:46:49 GMT
• Title: A Large-Scale Sensitivity Analysis on Latent Embeddings and Dimensionality Reductions for Text Spatializations
• Authors: Daniel Atzberger, Tim Cech, Willy Scheibel, Jürgen Döllner, Michael Behrisch, Tobias Schreck,
• Abstract summary: The semantic similarity between documents of a text corpus can be visualized using map-like metaphors. These scatterplot layouts result from a dimensionality reduction on the document-term matrix or a representation within a latent embedding. We present a sensitivity study that analyzes the stability of these layouts concerning changes in the text corpora.
• Score: 4.810926556822174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The semantic similarity between documents of a text corpus can be visualized using map-like metaphors based on two-dimensional scatterplot layouts. These layouts result from a dimensionality reduction on the document-term matrix or a representation within a latent embedding, including topic models. Thereby, the resulting layout depends on the input data and hyperparameters of the dimensionality reduction and is therefore affected by changes in them. Furthermore, the resulting layout is affected by changes in the input data and hyperparameters of the dimensionality reduction. However, such changes to the layout require additional cognitive efforts from the user. In this work, we present a sensitivity study that analyzes the stability of these layouts concerning (1) changes in the text corpora, (2) changes in the hyperparameter, and (3) randomness in the initialization. Our approach has two stages: data measurement and data analysis. First, we derived layouts for the combination of three text corpora and six text embeddings and a grid-search-inspired hyperparameter selection of the dimensionality reductions. Afterward, we quantified the similarity of the layouts through ten metrics, concerning local and global structures and class separation. Second, we analyzed the resulting 42817 tabular data points in a descriptive statistical analysis. From this, we derived guidelines for informed decisions on the layout algorithm and highlight specific hyperparameter settings. We provide our implementation as a Git repository at https://github.com/hpicgs/Topic-Models-and-Dimensionality-Reduction-Sensitivity-Study and results as Zenodo archive at https://doi.org/10.5281/zenodo.12772898.

Related papers

• Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective [50.261681681643076]
  We propose a novel metric called SemVarEffect and a benchmark named SemVarBench to evaluate the causality between semantic variations in inputs and outputs in text-to-image synthesis. Our work establishes an effective evaluation framework that advances the T2I synthesis community's exploration of human instruction understanding.
  arXiv  Detail & Related papers  (2024-10-14T08:45:35Z)
• WorDepth: Variational Language Prior for Monocular Depth Estimation [47.614203035800735]
  We investigate whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. We focus on monocular depth estimation, the problem of predicting a dense depth map from a single image. Our approach is trained alternatingly between the text and image branches.
  arXiv  Detail & Related papers  (2024-04-04T17:54:33Z)
• Dynamic Visual Semantic Sub-Embeddings and Fast Re-Ranking [0.5242869847419834]
  We propose a Dynamic Visual Semantic Sub-Embeddings framework (DVSE) to reduce the information entropy. To encourage the generated candidate embeddings to capture various semantic variations, we construct a mixed distribution. We compare the performance with existing set-based method using four image feature encoders and two text feature encoders on three benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-15T04:39:11Z)
• A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions [50.469491454128246]
  We use text as the guidance to create graphic layouts, i.e., Text-to-labeled, aiming to lower the design barriers. Text-to-labeled is a challenging task, because it needs to consider the implicit, combined, and incomplete constraints from text. We present a two-stage approach, named parse-then-place, to address this problem.
  arXiv  Detail & Related papers  (2023-08-24T10:37:00Z)
• Large-Scale Evaluation of Topic Models and Dimensionality Reduction Methods for 2D Text Spatialization [2.6034734004409303]
  We show that interpretable topic models are beneficial for capturing the structure of text corpora. We propose guidelines for the effective design of text spatializations based on topic models and dimensionality reductions.
  arXiv  Detail & Related papers  (2023-07-17T14:08:25Z)
• Attention Map Guided Transformer Pruning for Edge Device [98.42178656762114]
  Vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. We propose a novel attention map guided (AMG) transformer pruning method, which removes both redundant tokens and heads. Comprehensive experiments on Occluded DukeMTMC and Market-1501 demonstrate the effectiveness of our proposals.
  arXiv  Detail & Related papers  (2023-04-04T01:51:53Z)
• Changepoint Analysis of Topic Proportions in Temporal Text Data [1.8262547855491456]
  We build a specialised temporal topic model with provisions for changepoints in the distribution of topic proportions. We use sample splitting to estimate topic polytopes first and then apply a likelihood ratio statistic. We obtain some historically well-known changepoints and discover some new ones.
  arXiv  Detail & Related papers  (2021-11-29T17:20:51Z)
• Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization [81.26077816854449]
  We first explore the use of constituency parse trees for encoding structured input. Second, we augment the structured input with commonsense information and study the impact of this external knowledge on the generation of visual story. Third, we incorporate visual structure via bounding boxes and dense captioning to provide feedback about the characters/objects in generated images.
  arXiv  Detail & Related papers  (2021-10-21T00:16:02Z)
• Index $t$-SNE: Tracking Dynamics of High-Dimensional Datasets with Coherent Embeddings [1.7188280334580195]
  This paper presents a methodology to reuse an embedding to create a new one, where cluster positions are preserved. The proposed algorithm has the same complexity as the original $t$-SNE to embed new items, and a lower one when considering the embedding of a dataset sliced into sub-pieces.
  arXiv  Detail & Related papers  (2021-09-22T06:45:37Z)
• Semantic Change Detection with Asymmetric Siamese Networks [71.28665116793138]
  Given two aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. We present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures.
  arXiv  Detail & Related papers  (2020-10-12T13:26:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.