Look, Read and Ask: Learning to Ask Questions by Reading Text in Images
This addresses the need for conversational agents to generate questions from visual and textual inputs, though it is incremental as it builds on existing text-based visual question answering tasks.
The paper tackles the problem of text-based visual question generation (TextVQG), which involves generating natural language questions from images and extracted text (OCR tokens) where the text is the answer. The proposed model, OLRA, outperforms baselines on public benchmarks, generating questions similar to manually curated datasets and achieving significant gains in text generation metrics.
We present a novel problem of text-based visual question generation or TextVQG in short. Given the recent growing interest of the document image analysis community in combining text understanding with conversational artificial intelligence, e.g., text-based visual question answering, TextVQG becomes an important task. TextVQG aims to generate a natural language question for a given input image and an automatically extracted text also known as OCR token from it such that the OCR token is an answer to the generated question. TextVQG is an essential ability for a conversational agent. However, it is challenging as it requires an in-depth understanding of the scene and the ability to semantically bridge the visual content with the text present in the image. To address TextVQG, we present an OCR consistent visual question generation model that Looks into the visual content, Reads the scene text, and Asks a relevant and meaningful natural language question. We refer to our proposed model as OLRA. We perform an extensive evaluation of OLRA on two public benchmarks and compare them against baselines. Our model OLRA automatically generates questions similar to the public text-based visual question answering datasets that were curated manually. Moreover, we significantly outperform baseline approaches on the performance measures popularly used in text generation literature.