IEEE VIS 2024 Content: VADIS: A Visual Analytics Pipeline for Dynamic Document Representation and Information Seeking

Best Paper Award

VADIS: A Visual Analytics Pipeline for Dynamic Document Representation and Information Seeking

Rui Qiu - Ohio State University, Columbus, United States

Yamei Tu - The Ohio State University, Columbus, United States

Po-Yin Yen - Washington University School of Medicine in St. Louis, St. Louis, United States

Han-Wei Shen - The Ohio State University , Columbus , United States

Room: Bayshore I + II + III

2024-10-15T16:55:00ZGMT-0600Change your timezone on the schedule page
2024-10-15T16:55:00Z
Exemplar figure, described by caption below
Traditional document maps cluster documents based on static embeddings, leading to confusing grouping with inconsistent semantic concepts. We propose Prompt-based Attention Model (PAM) that generates prompt-specific document representations to better align with human interest. Recognizing that not all documents are equally relevant to a user’s specific interest, we present Relevance-preserving mapping to project documents based on both their relevance to the user’s interest, and their inter-similarity under user’s interest. The mapping features a circular layout that centralizes the most pertinent documents, which aligns with both human’s natural viewing pattern and the distribution of documents’ relevance.
Fast forward
Full Video
Keywords

Attention visualization, dynamic document representation, document visualization, biomedical information seeking

Abstract

In the biomedical domain, visualizing the document embeddings of an extensive corpus has been widely used in information-seeking tasks. However, three key challenges with existing visualizations make it difficult for clinicians to find information efficiently. First, the document embeddings used in these visualizations are generated statically by pretrained language models, which cannot adapt to the user's evolving interest. Second, existing document visualization techniques cannot effectively display how the documents are relevant to users’ interest, making it difficult for users to identify the most pertinent information. Third, existing embedding generation and visualization processes suffer from a lack of interpretability, making it difficult to understand, trust and use the result for decision-making. In this paper, we present a novel visual analytics pipeline for user-driven document representation and iterative information seeking (VADIS). VADIS introduces a prompt-based attention model (PAM) that generates dynamic document embedding and document relevance adjusted to the user's query. To effectively visualize these two pieces of information, we design a new document map that leverages a circular grid layout to display documents based on both their relevance to the query and the semantic similarity. Additionally, to improve the interpretability, we introduce a corpus-level attention visualization method to improve the user's understanding of the model focus and to enable the users to identify potential oversight. This visualization, in turn, empowers users to refine, update and introduce new queries, thereby facilitating a dynamic and iterative information-seeking experience. We evaluated VADIS quantitatively and qualitatively on a real-world dataset of biomedical research papers to demonstrate its effectiveness.