Low-Resource Language Processing: An OCR-Driven Summarization and Translation Pipeline

TL;DR

This paper introduces an end-to-end multilingual document processing pipeline that leverages OCR and large language models to extract, translate, summarize, and analyze information from image-based documents in low-resource languages.

Contribution

It presents a novel integrated system combining OCR, LLM APIs, and auxiliary modules for comprehensive multilingual document understanding in low-resource languages.

Findings

Effective extraction of text from images in multiple languages.

Successful cross-lingual translation and summarization using LLM APIs.

Enhanced document comprehension with sentiment, topic, and date analysis.

Abstract

This paper presents an end-to-end suite for multilingual information extraction and processing from image-based documents. The system uses Optical Character Recognition (Tesseract) to extract text in languages such as English, Hindi, and Tamil, and then a pipeline involving large language model APIs (Gemini) for cross-lingual translation, abstractive summarization, and re-translation into a target language. Additional modules add sentiment analysis (TensorFlow), topic classification (Transformers), and date extraction (Regex) for better document comprehension. Made available in an accessible Gradio interface, the current research shows a real-world application of libraries, models, and APIs to close the language gap and enhance access to information in image media across different linguistic environments