Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Bridging Queries and Tables through Entities in Table Retrieval

Da Li, Keping Bi, Jiafeng Guo, Xueqi Cheng

TL;DR

This work investigates the important role of entities in table retrieval from a statistical perspective and proposes an entity-enhanced training framework, which is plug-and-play and flexible, making it easy to integrate into existing table retriever training processes.

Abstract

Table retrieval is essential for accessing information stored in structured tabular formats; however, it remains less explored than text retrieval. The content of the table primarily consists of phrases and words, which include a large number of entities, such as time, locations, persons, and organizations. Entities are well-studied in the context of text retrieval, but there is a noticeable lack of research on their applications in table retrieval. In this work, we explore how to leverage entities in tables to improve retrieval performance. First, we investigate the important role of entities in table retrieval from a statistical perspective and propose an entity-enhanced training framework. Subsequently, we use the type of entities to highlight entities instead of introducing an external knowledge base. Moreover, we design an interaction paradigm based on entity representations. Our proposed framework is plug-and-play and flexible, making it easy to integrate into existing table retriever training processes. Empirical results on two table retrieval benchmarks, NQ-TABLES and OTT-QA, show that our proposed framework is both simple and effective in enhancing existing retrievers. We also conduct extensive analyses to confirm the efficacy of different components. Overall, our work provides a promising direction for elevating table retrieval, enlightening future research in this area.

Bridging Queries and Tables through Entities in Table Retrieval

TL;DR

This work investigates the important role of entities in table retrieval from a statistical perspective and proposes an entity-enhanced training framework, which is plug-and-play and flexible, making it easy to integrate into existing table retriever training processes.

Abstract

Table retrieval is essential for accessing information stored in structured tabular formats; however, it remains less explored than text retrieval. The content of the table primarily consists of phrases and words, which include a large number of entities, such as time, locations, persons, and organizations. Entities are well-studied in the context of text retrieval, but there is a noticeable lack of research on their applications in table retrieval. In this work, we explore how to leverage entities in tables to improve retrieval performance. First, we investigate the important role of entities in table retrieval from a statistical perspective and propose an entity-enhanced training framework. Subsequently, we use the type of entities to highlight entities instead of introducing an external knowledge base. Moreover, we design an interaction paradigm based on entity representations. Our proposed framework is plug-and-play and flexible, making it easy to integrate into existing table retriever training processes. Empirical results on two table retrieval benchmarks, NQ-TABLES and OTT-QA, show that our proposed framework is both simple and effective in enhancing existing retrievers. We also conduct extensive analyses to confirm the efficacy of different components. Overall, our work provides a promising direction for elevating table retrieval, enlightening future research in this area.

Paper Structure

This paper contains 29 sections, 11 equations, 4 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Table Search
  4. Table Retrieval
  5. Table Reranking
  6. Entity-Enhanced Retrieval
  7. Preliminary Study
  8. Entity Coverage in Table Retrieval
  9. Effect of Entities in Relevance Matching
  10. Distribution of Entity Type in Tables
  11. Entity-Enhanced Training Framework (EE) for Table Retrieval
  12. Entity Type Embedding
  13. Interaction for Entity Representation
  14. Based on Dense Retrievers
  15. Based on Sparse Retrievers
  16. ...and 14 more sections

Figures (4)

  • Figure 1: Entity Type Distribution in the Table Retrieval Benchmark. The inner ring visualizes the statistics for queries, whereas the outer ring represents those for tables. Entities of the same type are represented by the same color.
  • Figure 2: Illustration of Entity-Enhanced Training Framework. Left is the process of encoding and we use the input of the table as an example. The right is the interaction based on entity representations.
  • Figure 3: Effect of Entity Matching Weights on BIBERT and SPLADE.
  • Figure 4: Retrieval Result Comparison between EE-BIBIERT and BIBERT.