go-v.orgdoi

Visual Analysis of Semantic Paraphrase Embebdding Projection Stability

Manuel Schmidt, Daniel A. Keim, Frederik L. Dennig · KOPS (University of Konstanz) · 2026

  • DOI 10.2312/mlvis.20261002
  • Publisher University of Konstanz
  • Type conference-paper
  • Issued 2026

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

KOPS (University of Konstanz) · University of Konstanz · conference-paper · 2026

Abstract

Sentence embeddings are widely used as a proxy for semantic similarity in applications such as passage retrieval for question answering. A common approach to inspect such embeddings is to project them into a lower dimension. However, neither small embedding distance nor proximity in a low-dimensional projection guarantees semantic equivalence. We present an interactive analysis tool for exploring this mismatch on paraphrase pairs from the Quora Question Pairs dataset. The system combines an interactive UMAP projection, editable sentence variants, and a heatmap for token sensitivity analysis.

This enables users to inspect whether local neighborhoods in the projection reflect relationships in the original embedding space and to identify tokens influencing the sentence representation. In a qualitative case study, we show failure modes, including paraphrase pairs with unexpectedly large embedding distances and non-equivalent questions in which local neighborhoods are not defined by semantic similarity. Our results show that visual proximity should be treated as an exploratory cue rather than a semantic equivalence.

Open the resolved locator · 10.2312/mlvis.20261002

Metadata licence: OpenAlex metadata (CC0)