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

2025-05-16

AI Summary

This study addresses the challenges of multilingual image-document information extraction and weak support for low-resource languages by proposing an end-to-end, lightweight multi-task framework. Methodologically, it introduces the first OCR–large language model (LLM) collaborative pipeline—integrating Tesseract-based cross-lingual OCR, machine translation, abstractive summarization, back-translation, TensorFlow-powered sentiment analysis, Hugging Face Transformers-based topic classification, and rule-based date extraction. The system supports English, Hindi, Tamil, and other languages, achieving high-accuracy cross-lingual understanding and generation on real-world document images. Key contributions include: (1) the first lightweight OCR–LLM co-processing architecture explicitly designed for low-resource languages; (2) significant improvements in document semantic accessibility via joint multi-task optimization; and (3) an interactive Gradio interface that bridges linguistic divides and enhances information access for multilingual users.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Information Extraction
• Computer Vision: Language and Vision

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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

Problem

• Develops OCR-driven multilingual text extraction from images
• Provides cross-lingual translation and summarization using LLMs
• Enhances document comprehension with sentiment/topic/date analysis

Innovation

• OCR-driven text extraction for multilingual documents
• LLM APIs for translation and summarization
• Integrated sentiment and topic analysis modules