ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning

• URL: http://arxiv.org/abs/2507.07306v1
• Date: Wed, 09 Jul 2025 22:05:46 GMT
• Title: ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning
• Authors: Yichen Lu, Wei Dai, Jiaen Liu, Ching Wing Kwok, Zongheng Wu, Xudong Xiao, Ao Sun, Sheng Fu, Jianyuan Zhan, Yian Wang, Takatomo Saito, Sicheng Lai,
• Abstract summary: ViDove is a translation agent system designed for multimodal input.<n>We introduce DoveBench, a new benchmark for long-form automatic video subtitling and translation.
• Score: 5.544427667851464
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: LLM-based translation agents have achieved highly human-like translation results and are capable of handling longer and more complex contexts with greater efficiency. However, they are typically limited to text-only inputs. In this paper, we introduce ViDove, a translation agent system designed for multimodal input. Inspired by the workflow of human translators, ViDove leverages visual and contextual background information to enhance the translation process. Additionally, we integrate a multimodal memory system and long-short term memory modules enriched with domain-specific knowledge, enabling the agent to perform more accurately and adaptively in real-world scenarios. As a result, ViDove achieves significantly higher translation quality in both subtitle generation and general translation tasks, with a 28% improvement in BLEU scores and a 15% improvement in SubER compared to previous state-of-the-art baselines. Moreover, we introduce DoveBench, a new benchmark for long-form automatic video subtitling and translation, featuring 17 hours of high-quality, human-annotated data. Our code is available here: https://github.com/pigeonai-org/ViDove

Related papers

• Multilingual Contextualization of Large Language Models for Document-Level Machine Translation [30.005159724115824]
  Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation.<n>We propose a method to improve LLM-based long-document translation through targeted fine-tuning on high-quality document-level data.<n>Our approach supports multiple translation paradigms, including direct document-to-document and chunk-level translation.
  arXiv  Detail & Related papers  (2025-04-16T14:52:22Z)
• Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues [56.038123093599815]
  Our objective is to translate continuous sign language into spoken language text.<n>We incorporate additional contextual cues together with the signing video.<n>We show that our contextual approach significantly enhances the quality of the translations.
  arXiv  Detail & Related papers  (2025-01-16T18:59:03Z)
• DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory [96.35468670508476]
  We introduce DelTA, a Document-levEL Translation Agent for large language models (LLMs)<n>DelTA features a multi-level memory structure that stores information across various granularities and spans.<n> Experimental results indicate that DelTA significantly outperforms strong baselines in terms of translation consistency and quality.
  arXiv  Detail & Related papers  (2024-10-10T17:30:09Z)
• (Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts [56.7988577327046]
  We introduce TransAgents, a novel multi-agent framework that simulates the roles and collaborative practices of a human translation company.<n>Our findings highlight the potential of multi-agent collaboration in enhancing translation quality, particularly for longer texts.
  arXiv  Detail & Related papers  (2024-05-20T05:55:08Z)
• Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing [12.843274390224853]
  Large Language Models (LLM's) have demonstrated considerable success in various Natural Language Processing tasks. We show that they have yet to attain state-of-the-art performance in Neural Machine Translation. We propose adapting LLM's as Automatic Post-Editors (APE) rather than direct translators.
  arXiv  Detail & Related papers  (2023-10-23T12:22:15Z)
• Exploring Human-Like Translation Strategy with Large Language Models [93.49333173279508]
  Large language models (LLMs) have demonstrated impressive capabilities in general scenarios. This work proposes the MAPS framework, which stands for Multi-Aspect Prompting and Selection. We employ a selection mechanism based on quality estimation to filter out noisy and unhelpful knowledge.
  arXiv  Detail & Related papers  (2023-05-06T19:03:12Z)
• Modeling Context With Linear Attention for Scalable Document-Level Translation [72.41955536834702]
  We investigate the efficacy of a recent linear attention model on document translation and augment it with a sentential gate to promote a recency inductive bias. We show that sentential gating further improves translation quality on IWSLT.
  arXiv  Detail & Related papers  (2022-10-16T03:41:50Z)
• Improving Multilingual Translation by Representation and Gradient Regularization [82.42760103045083]
  We propose a joint approach to regularize NMT models at both representation-level and gradient-level. Our results demonstrate that our approach is highly effective in both reducing off-target translation occurrences and improving zero-shot translation performance.
  arXiv  Detail & Related papers  (2021-09-10T10:52:21Z)
• Exploiting BERT For Multimodal Target SentimentClassification Through Input Space Translation [75.82110684355979]
  We introduce a two-stream model that translates images in input space using an object-aware transformer. We then leverage the translation to construct an auxiliary sentence that provides multimodal information to a language model. We achieve state-of-the-art performance on two multimodal Twitter datasets.
  arXiv  Detail & Related papers  (2021-08-03T18:02:38Z)
• ViTA: Visual-Linguistic Translation by Aligning Object Tags [7.817598216459955]
  Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. We propose our system for the Multimodal Translation Task of WAT 2021 from English to Hindi.
  arXiv  Detail & Related papers  (2021-06-01T06:19:29Z)
• Simultaneous Machine Translation with Visual Context [42.88121241096681]
  Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. We analyse the impact of different multimodal approaches and visual features on state-of-the-art SiMT frameworks.
  arXiv  Detail & Related papers  (2020-09-15T18:19:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.