paper-with-me

Papers

Explainable Point-Based Document Visualizations

2021-09-28 · Primož Godec, Nikola Ðukić, Ajda Pretnar, Vesna Tanko, Lan Žagar, Blaž Zupan

Two-dimensional data maps can visually reveal information about the relations between data instances. Popular techniques to construct data maps are t-SNE and UMAP. The resulting point-based visualizations, though, provide information only through their interpretation. We here consider a set of abstracts from the articles on longevity to argue for using keyword extraction methods to label clusters of documents in the map. Among the considered approaches, the best results were obtained by recently proposed YAKE!. Surprisingly, a classical TF-IDF term ranking outperformed graph and embedding-based techniques.

📄 PDF Abstract BibTeX arXiv:2110.00462

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesKeyword Extraction

Similar Papers 제목 키워드 기반

Explainable AI for tailored electricity consumption feedback -- an experimental evaluation of visualizations

2022-08-24 · Jacqueline Wastensteiner, Tobias M. Weiss, Felix Haag, Konstantin Hopf

Machine learning (ML) methods can effectively analyse data, recognize patterns in them, and make high-quality predictions. Good predictions usually come along with "black-box" models that are unable to present the detect…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Time SeriesTime Series Analysis

SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches

2026-06-16 · Wencan Zhang, Mario Michelessa, Xuejun Zhao, Brian Y. Lim arxiv

Saliency map visualizations explain image-based AI predictions by pointing to regions, but these are often unintuitive and semantically unclear, leaving an interpretability gap. We argue that AI explanations should be in…

Visualization for Recommendation Explainability: A Survey and New Perspectives

2023-05-19 · Mohamed Amine Chatti, Mouadh Guesmi, Arham Muslim

Providing system-generated explanations for recommendations represents an important step towards transparent and trustworthy recommender systems. Explainable recommender systems provide a human-understandable rationale f…

Explainable RecommendationRecommendation SystemsSurvey

Creating an Explainable Intrusion Detection System Using Self Organizing Maps

2022-07-15 · Jesse Ables, Thomas Kirby, William Anderson, Sudip Mittal 외

Modern Artificial Intelligence (AI) enabled Intrusion Detection Systems (IDS) are complex black boxes. This means that a security analyst will have little to no explanation or clarification on why an IDS model made a par…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Explanation GenerationIntrusion Detection

Visualizing Temporal Topic Embeddings with a Compass

2024-09-16 · Daniel Palamarchuk, Lemara Williams, Brian Mayer, Thomas Danielson 외

Dynamic topic modeling is useful at discovering the development and change in latent topics over time. However, present methodology relies on algorithms that separate document and word representations. This prevents the …

DiversityDynamic Topic ModelingWord Embeddings