Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Varnosfaderani, Shirin Dabbaghi, Kruengkrai, Canasai, Yahyapour, Ramin, Yamagishi, Junichi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910383074181120
author Varnosfaderani, Shirin Dabbaghi
Kruengkrai, Canasai
Yahyapour, Ramin
Yamagishi, Junichi
author_facet Varnosfaderani, Shirin Dabbaghi
Kruengkrai, Canasai
Yahyapour, Ramin
Yamagishi, Junichi
contents FEVEROUS is a benchmark and research initiative focused on fact extraction and verification tasks involving unstructured text and structured tabular data. In FEVEROUS, existing works often rely on extensive preprocessing and utilize rule-based transformations of data, leading to potential context loss or misleading encodings. This paper introduces a simple yet powerful model that nullifies the need for modality conversion, thereby preserving the original evidence's context. By leveraging pre-trained models on diverse text and tabular datasets and by incorporating a lightweight attention-based mechanism, our approach efficiently exploits latent connections between different data types, thereby yielding comprehensive and reliable verdict predictions. The model's modular structure adeptly manages multi-modal information, ensuring the integrity and authenticity of the original evidence are uncompromised. Comparative analyses reveal that our approach exhibits competitive performance, aligning itself closely with top-tier models on the FEVEROUS benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17361
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model
Varnosfaderani, Shirin Dabbaghi
Kruengkrai, Canasai
Yahyapour, Ramin
Yamagishi, Junichi
Computation and Language
Artificial Intelligence
FEVEROUS is a benchmark and research initiative focused on fact extraction and verification tasks involving unstructured text and structured tabular data. In FEVEROUS, existing works often rely on extensive preprocessing and utilize rule-based transformations of data, leading to potential context loss or misleading encodings. This paper introduces a simple yet powerful model that nullifies the need for modality conversion, thereby preserving the original evidence's context. By leveraging pre-trained models on diverse text and tabular datasets and by incorporating a lightweight attention-based mechanism, our approach efficiently exploits latent connections between different data types, thereby yielding comprehensive and reliable verdict predictions. The model's modular structure adeptly manages multi-modal information, ensuring the integrity and authenticity of the original evidence are uncompromised. Comparative analyses reveal that our approach exhibits competitive performance, aligning itself closely with top-tier models on the FEVEROUS benchmark.
title Bridging Textual and Tabular Worlds for Fact Verification: A Lightweight, Attention-Based Model
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.17361