Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Conversational Exploratory Search of Scholarly Publications Using Knowledge Graphs

Phillip Schneider, Florian Matthes

TL;DR

A conversational search system for exploring scholarly publications using a knowledge graph is developed, detailing its architecture and functional components and demonstrating how the conversational interface compares against a graphical interface with traditional text search.

Abstract

Traditional search methods primarily depend on string matches, while semantic search targets concept-based matches by recognizing underlying intents and contextual meanings of search terms. Semantic search is particularly beneficial for discovering scholarly publications where differences in vocabulary between users' search terms and document content are common, often yielding irrelevant search results. Many scholarly search engines have adopted knowledge graphs to represent semantic relations between authors, publications, and research concepts. However, users may face challenges when navigating these graphical search interfaces due to the complexity and volume of data, which impedes their ability to discover publications effectively. To address this problem, we developed a conversational search system for exploring scholarly publications using a knowledge graph. We outline the methodical approach for designing and implementing the proposed system, detailing its architecture and functional components. To assess the system's effectiveness, we employed various performance metrics and conducted a human evaluation with 40 participants, demonstrating how the conversational interface compares against a graphical interface with traditional text search. The findings from our evaluation provide practical insights for advancing the design of conversational search systems.

Conversational Exploratory Search of Scholarly Publications Using Knowledge Graphs

TL;DR

A conversational search system for exploring scholarly publications using a knowledge graph is developed, detailing its architecture and functional components and demonstrating how the conversational interface compares against a graphical interface with traditional text search.

Abstract

Traditional search methods primarily depend on string matches, while semantic search targets concept-based matches by recognizing underlying intents and contextual meanings of search terms. Semantic search is particularly beneficial for discovering scholarly publications where differences in vocabulary between users' search terms and document content are common, often yielding irrelevant search results. Many scholarly search engines have adopted knowledge graphs to represent semantic relations between authors, publications, and research concepts. However, users may face challenges when navigating these graphical search interfaces due to the complexity and volume of data, which impedes their ability to discover publications effectively. To address this problem, we developed a conversational search system for exploring scholarly publications using a knowledge graph. We outline the methodical approach for designing and implementing the proposed system, detailing its architecture and functional components. To assess the system's effectiveness, we employed various performance metrics and conducted a human evaluation with 40 participants, demonstrating how the conversational interface compares against a graphical interface with traditional text search. The findings from our evaluation provide practical insights for advancing the design of conversational search systems.
Paper Structure (16 sections, 5 figures, 5 tables)

This paper contains 16 sections, 5 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Conversational Search System
  4. System Architecture
  5. Knowledge Graph and Vector Database
  6. Results and Discussion
  7. Model Training and Evaluation
  8. Research Topic Classification.
  9. Article Text Clustering.
  10. Comparative Text Summarization.
  11. Human Evaluation
  12. Experiment Design.
  13. Quantitative Analysis of Evaluation Metrics.
  14. Qualitative Analysis of Participant Feedback.
  15. Conclusion
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Architectural components of the conversational exploratory search system.
  • Figure 2: Comparison of accuracy and F1-scores for three topic classification approaches.
  • Figure 3: Comparison of rating distribution between the conversational and graphical user interface (UI) for readability, correctness, usefulness, and overall satisfaction. The thick line intersecting the box marks the median.
  • Figure 4: Conversational search flow illustrated as dialogue states (S1-S7). The three-phase search process encompasses: first, identifying a research topic (S3); second, choosing clusters of publications (S4); and third, comparing publications via short summaries (S5-S6).
  • Figure 5: Semantic data model of the scholarly knowledge graph.