Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-6

Table Retrieval

3260 papers • 126 benchmarks • 313 datasets

When given a query, the goal of this task is to retrieve a relevant table from a (potentially large) collection of tables. The query could be a single sentence (such as a question), or it could also be a conversation. As for the retrieval, the tables could be in the raw form (i.e. the values of each cells), the metadata (such as the title, description), or summary statistics.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in table-retrieval-18

Trend

Dataset

Best Model

Actions

Statcan Dialogue Dataset

Statcan Dialogue Dataset

Libraries

i

Use these libraries to find table-retrieval-18 models and implementations

Datasets

Statcan Dialogue Dataset

Statcan Dialogue Dataset

Subtasks

No subtasks available.

Most implemented papers

Ad Hoc Table Retrieval using Semantic Similarity

K. Balog, Shuo Zhang•Thu Feb 15 2018

This work introduces and addresses the problem of ad hoc table retrieval: answering a keyword query with a ranked list of tables, and introduces various similarity measures for matching those semantic representations.

132

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval

K. Balog, Li Deng, Shuo Zhang•Thu May 30 2019

Evaluation results show that table embeddings can significantly improve upon the performance of state-of-the-art baselines and be utilized in table-related tasks, row population, column population, and table retrieval.

126 0

Table Search Using a Deep Contextualized Language Model

Zhiyu Chen, M. Trabelsi, Jeff Heflin, Yinan Xu, Brian D. Davison•Mon May 18 2020

This paper investigates how to encode table content considering the table structure and input length limit of BERT and proposes an approach that incorporates features from prior literature on table retrieval and jointly trains them with BERT.

67 0

Retrieving Complex Tables with Multi-Granular Graph Representation Learning

Fei Wang, Muhao Chen, J. Pujara, Kexuan Sun, Pedro A. Szekely•Mon May 03 2021

Graph-based Table Retrieval (GTR), a generalizable NLTR framework with multi-granular graph representation learning, which incorporates a self-supervised pre-training task based on graph-context matching to enhance the robustness and generalizability of the model.

56 0

WTR: A Test Collection for Web Table Retrieval

Zhiyu Chen, Shuo Zhang, B. Davison•Tue May 04 2021

This work describes the development, characteristics and availability of a test collection for the task of Web table retrieval, which uses a large-scale Web Table Corpora extracted from the Common Crawl and shows that proper usage of context labels can benefit previous table retrieval methods.

12 0

Semantic Table Retrieval using Keyword and Table Queries

K. Balog, Shuo Zhang•Wed May 12 2021

This work proposes a semantic table retrieval framework for matching information needs (keyword or table queries) against tables in multiple semantic spaces and introduces various similarity measures for matching those semantic representations.

17 0

StruBERT: Structure-aware BERT for Table Search and Matching

Shuo Zhang, Zhiyu Chen, M. Trabelsi, Jeff Heflin, Brian D. Davison•Sat Mar 26 2022

StruBERT is proposed, a structure-aware BERT model that fuses the textual and structural information of a data table to produce context-aware representations for both textual and tabular content of aData table.

51 0

Table Retrieval May Not Necessitate Table-specific Model Design

Graham Neubig, Zhengbao Jiang, Zhiruo Wang, Eric Nyberg•Wed May 18 2022

The task of table retrieval is focused on, and it is found that DPR performs well without any table-specific design and training, and even achieves superior results compared to DTR when fine-tuned on properly linearized tables.

19 0

cTBLS: Augmenting Large Language Models with Conversational Tables

Larry Heck, Anirudh S. Sundar•Mon Mar 20 2023

Conversational Tables cTBLS is introduced, a three-step architecture to retrieve and generate dialogue responses grounded on retrieved tabular information to improve accuracy and performance and judge informativeness to be 4x better than the previous state-of-the-art.

12 0

Adding a benchmark result helps the community track progress.

Table Retrieval | State-of-the-Art