paper-with-me

홈 › Papers

TabSD: Large Free-Form Table Question Answering with SQL-Based Table Decomposition

2025-02-19 · Yuxiang Wang, Junhao Gan, Jianzhong Qi

Question answering on free-form tables (TableQA) is challenging due to the absence of predefined schemas and the presence of noise in large tables. While Large Language Models (LLMs) have shown promise in TableQA, they struggle with large free-form tables and noise sensitivity. To address these challenges, we propose TabSD, a SQL-based decomposition model that enhances LLMs' ability to process large free-form tables. TabSD generates SQL queries to guide the table decomposition, remove noise, and processes sub-tables for better answer generation. Additionally, SQL Verifier refines SQL outputs to enhance decomposition accuracy. We introduce two TableQA datasets with large free-form tables, SLQA and SEQA, which consist solely of large free-form tables and will be publicly available. Experimental results on four benchmark datasets demonstrate that TABSD outperforms the best-existing baseline models by 23.07%, 2.84%, 23.24% and 9.32% in accuracy, respectively, highlighting its effectiveness in handling large and noisy free-form tables.

📄 PDF Abstract BibTeX arXiv:2502.13422

Code (0)

등록된 구현이 없습니다.

Tasks

Answer GenerationFormQuestion Answering

Similar Papers 제목 키워드 기반

FeTaQA: Free-form Table Question Answering

2021-04-01 · Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin 외

Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to include questions that require complex rea…

FormQuestion AnsweringRetrievalSemantic Parsing+1

Learning Representations for Zero-Shot Retrieval over Structured Data

2021-10-29 · Harsh Kohli

Large Scale Question-Answering systems today are widely used in downstream applications such as chatbots and conversational dialogue agents. Typically, such systems consist of an Answer Passage retrieval layer coupled wi…

Passage RetrievalQuestion AnsweringReading ComprehensionRetrieval

FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase

2019-06-01 · NAACL 2019 6 · Kelvin Jiang, Dekun Wu, Hui Jiang

In this paper, we present a new data set, named FreebaseQA, for open-domain factoid question answering (QA) tasks over structured knowledge bases, like Freebase. The data set is generated by matching trivia-type question…

Question Answeringset matchingTAG

TableQuery: Querying tabular data with natural language

2022-01-27 · Abhijith Neil Abraham, Fariz Rahman, Damanpreet Kaur

This paper presents TableQuery, a novel tool for querying tabular data using deep learning models pre-trained to answer questions on free text. Existing deep learning methods for question answering on tabular data have v…

Deep LearningNatural Language QueriesQuestion Answering

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

2020-05-17 · ACL 2020 6 · Pengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian Riedel

Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks. Such models are typically trained on free-form NL text, hence may not be suitable f…

FormSemantic ParsingText to SQLText-To-SQL