5 papers
Video-guided Machine Translation with Global Video Context
Jian Chen, JinZe Lv, Zi Long +1
Video-guided Multimodal Translation (VMT) has advanced significantly in recent years. However, most existing methods rely on locally aligned video segments paired one-to-one with s…
TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries
Jinze Lv, Jian Chen, Zi Long +2
Most existing multimodal machine translation (MMT) datasets are predominantly composed of static images or short video clips, lacking extensive video data across diverse domains an…
A General Pseudonymization Framework for Cloud-Based LLMs: Replacing Privacy Information in Controlled Text Generation
Shilong Hou, Ruilin Shang, Zi Long +2
An increasing number of companies have begun providing services that leverage cloud-based large language models (LLMs), such as ChatGPT. However, this development raises substantia…
Multi-intent Aware Contrastive Learning for Sequential Recommendation
Junshu Huang, Zi Long, Xianghua Fu +1
Intent is a significant latent factor influencing user-item interaction sequences. Prevalent sequence recommendation models that utilize contrastive learning predominantly rely on…
Exploring the Necessity of Visual Modality in Multimodal Machine Translation using Authentic Datasets
Zi Long, Zhenhao Tang, Xianghua Fu +3
Recent research in the field of multimodal machine translation (MMT) has indicated that the visual modality is either dispensable or offers only marginal advantages. However, most…