Table Retrieval
13 papers with code • 1 benchmarks • 1 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.
Benchmarks
These leaderboards are used to track progress in Table Retrieval
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Statcan Dialogue Dataset
Most implemented papers
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
McGill-NLP/statcan-dialogue-dataset
•
•
We introduce the StatCan Dialogue Dataset consisting of 19, 379 conversation turns between agents working at Statistics Canada and online users looking for published data tables.
Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval
Open-domain table question answering aims to provide answers to a question by retrieving and extracting information from a large collection of tables.
Simulating Users in Interactive Web Table Retrieval
Our multi-perspective evaluation scheme reveals new insights about query strategies, the impact of modalities, and different user types in simulated WTR search sessions.
