CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering

2021/06/08 by Feifei Pan, Mustafa Canim, Pan, Feifei +7 · 1 citation
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Text and Document Classification Technologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2106.04441

openalex publication_date 2021/06/08 · openalex created_date 2021/06/22 · openalex updated_date 2026/07/28

Abstract

We present the first end-to-end, transformer-based table question answering (QA) system that takes natural language questions and massive table corpus as inputs to retrieve the most relevant tables and locate the correct table cells to answer the question. Our system, CLTR, extends the current state-of-the-art QA over tables model to build an end-to-end table QA architecture. This system has successfully tackled many real-world table QA problems with a simple, unified pipeline. Our proposed system can also generate a heatmap of candidate columns and rows over complex tables and allow users to quickly identify the correct cells to answer questions. In addition, we introduce two new open-domain benchmarks, E2E_WTQ and E2E_GNQ, consisting of 2,005 natural language questions over 76,242 tables. The benchmarks are designed to validate CLTR as well as accommodate future table retrieval and end-to-end table QA research and experiments. Our experiments demonstrate that our system is the current state-of-the-art model on the table retrieval task and produces promising results for end-to-end table QA.

Citations

• Compositional Semantic Parsing on Semi-Structured Tables
• TabMCQ: A Dataset of General Knowledge Tables and Multiple-choice Questions
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• Grammar-based Neural Text-to-SQL Generation
• Content Enhanced BERT-based Text-to-SQL Generation
• ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Cited by

• Improving Table Retrieval with Question Generation from Partial Tables

Related

• End-to-End Table Question Answering via Retrieval-Augmented Generation
• Capturing Row and Column Semantics in Transformer Based Question\n Answering over Tables
• Improving Table Retrieval with Question Generation from Partial Tables
• Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
• A Survey on Table Question Answering: Recent Advances