Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Wonjin, Kim, Kyumin, Lee, Sungjae, Lee, Jihun, Kim, Kwang In
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917928328232960
author Lee, Wonjin
Kim, Kyumin
Lee, Sungjae
Lee, Jihun
Kim, Kwang In
author_facet Lee, Wonjin
Kim, Kyumin
Lee, Sungjae
Lee, Jihun
Kim, Kwang In
contents Applying language models (LMs) to tables is challenging due to the inherent structural differences between two-dimensional tables and one-dimensional text for which the LMs were originally designed. Furthermore, when applying linearized tables to LMs, the maximum token lengths often imposed in self-attention calculations make it difficult to comprehensively understand the context spread across large tables. To address these challenges, we present PieTa (Piece of Table), a new framework for subtable-based question answering (QA). PieTa operates through an iterative process of dividing tables into smaller windows, using LMs to select relevant cells within each window, and merging these cells into a subtable. This multi-resolution approach captures dependencies across multiple rows and columns while avoiding the limitations caused by long context inputs. Instantiated as a simple iterative subtable union algorithm, PieTa demonstrates improved performance over previous subtable-based QA approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07629
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering
Lee, Wonjin
Kim, Kyumin
Lee, Sungjae
Lee, Jihun
Kim, Kwang In
Computation and Language
Artificial Intelligence
Applying language models (LMs) to tables is challenging due to the inherent structural differences between two-dimensional tables and one-dimensional text for which the LMs were originally designed. Furthermore, when applying linearized tables to LMs, the maximum token lengths often imposed in self-attention calculations make it difficult to comprehensively understand the context spread across large tables. To address these challenges, we present PieTa (Piece of Table), a new framework for subtable-based question answering (QA). PieTa operates through an iterative process of dividing tables into smaller windows, using LMs to select relevant cells within each window, and merging these cells into a subtable. This multi-resolution approach captures dependencies across multiple rows and columns while avoiding the limitations caused by long context inputs. Instantiated as a simple iterative subtable union algorithm, PieTa demonstrates improved performance over previous subtable-based QA approaches.
title Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.07629