Document Image Translation (DIT), which aims at translating documents in images from source language to the target, plays an important role in Document Intelligence. It requires a comprehensive understanding of document multi-modalities and a focused concentration on relevant textual regions during translation. However, most existing methods usually rely on the vanilla encoder-decoder paradigm, severely losing concentration on key regions that are especially crucial for complex-layout document translation. To tackle this issue, in this paper, we propose a new Query-Response DIT framework (QRDIT). QRDIT reformulates the DIT task into a parallel response/translation process of the multiple queries (i.e., relevant source texts), explicitly centralizing its focus toward the most relevant textual regions to ensure translation accuracy. A novel dynamic aggregation mechanism is also designed to enhance the text semantics in query features toward translation. Extensive experiments in four translation directions on three benchmarks demonstrate its state-of-the-art performance, showing significant translation quality improvements toward whole-page complex-layout document images.

Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. Previous efforts to enhance DIMT capability through Supervised Fine-Tuning (SFT) on the DIMT dataset often result in the forgetting of the model’s existing monolingual abilities, such as OCR. To address these challenges, we introduce a novel fine-tuning paradigm, named Synchronously Self-Reviewing (SSR) its OCR proficiency, inspired by the concept “Bilingual Cognitive Advantage”. Specifically, SSR prompts the model to generate OCR text before producing translation text, which allows the model to leverage its strong monolingual OCR ability while learning to translate text across languages. Comprehensive experiments demonstrate the proposed SSR learning helps mitigate catastrophic forgetting, improving the generalization ability of MLLMs on both OCR and DIMT tasks. The code will be released upon acceptance.

Machine learning (ML) has been successfully used as a prevalent approach to solving numerous NLP problems. However, the classic ML paradigm learns in isolation. That is, given a dataset, an ML algorithm is executed on the dataset to produce a model without using any related or prior knowledge. Although this type of isolated learning is very useful, it also has serious limitations as it does not accumulate knowledge learned in the past and use the knowledge to help future learning, which is the hallmark of human learning and human intelligence. Lifelong machine learning (LML) aims to achieve this capability. Specifically, it aims to design and develop computational learning systems and algorithms that learn as humans do, i.e., retaining the results learned in the past, abstracting knowledge from them, and using the knowledge to help future learning. In this tutorial, we will introduce the existing research of LML and to show that LML is very suitable for NLP tasks and has potential to help NLP make major progresses.