# Enhancing BERT-Based Visual Question Answering through Keyword-Driven Sentence Selection

Source: [Enhancing BERT-Based Visual Question Answering through Keyword-Driven Sentence Selection](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d893>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:51:52.116Z

Authors: Davide Napolitano, Lorenzo Vaiani, Luca Cagliero

Published: 2023-10-13T22:43:55.000Z

## Abstract

The Document-based Visual Question Answering competition addresses the automatic detection of parent-child relationships between elements in multi-page documents. The goal is to identify the document elements that answer a specific question posed in natural language. This paper describes the PoliTo's approach to addressing this task, in particular, our best solution explores a text-only approach, leveraging an ad hoc sampling strategy. Specifically, our approach leverages the Masked Language Modeling technique to fine-tune a BERT model, focusing on sentences containing sensitive keywords that also occur in the questions, such as references to tables or images. Thanks to the effectiveness of this approach, we are able to achieve high performance compared to baselines, demonstrating how our solution contributes positively to this task.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.09432>)

[PDF](<https://arxiv.org/pdf/2310.09432.pdf>)