Posts by Collection

TriFine: A Large-Scale Dataset of Vision-Audio-Subtitle for Tri-Modal Machine Translation and Benchmark with Fine-Grained Annotated Tags

Published in CCF B COLING 2025, 2025

This paper introduces TriFine, the first large-scale dataset for tri-modal (vision, audio, subtitle) machine translation with fine-grained annotated tags, and proposes a novel translation method FIAT that leverages this fine-grained information to achieve superior translation performance.

Recommended citation: TriFine: A Large-Scale Dataset of Vision-Audio-Subtitle for Tri-Modal Machine Translation and Benchmark with Fine-Grained Annotated Tags (Guan et al., COLING 2025)
Download Paper | Download Slides | Download Code | Download Dataset

SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation

Published in CCF B EMNLP 2025, 2025

This paper introduces SHIFT (Selected Helpful Informative Frame for Translation), a lightweight, plug-and-play framework for video-guided machine translation (VMT) that adaptively selects only the most informative video frame—or none when unnecessary—to improve translation quality and efficiency using multimodal large language models (MLLMs).

Recommended citation: SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation (Guan et al., EMNLP 2025)
Download Paper | Download Code

Oral Presentation on COLING 2025

Published: January 21, 2025

My paper, "TriFine: A Large-Scale Dataset of Vision-Audio-Subtitle for Tri-Modal Machine Translation and Benchmark with Fine-Grained Annotated Tags", was accepted as an Oral presentation in the Machine Translation track at COLING 2025. I presented it on January 21, 2025, at the ADNEC Centre Abu Dhabi, United Arab Emirates.

Teaching Assistant – Practical Natural Language Processing (Fall 2024)

Undergraduate course, School of Artificial Intelligence, University of Chinese Academy of Sciences, 2024

Served as a teaching assistant for the course Practical Natural Language Processing offered by Associate Professor Yang Zhao at the School of Artificial Intelligence, University of Chinese Academy of Sciences in Fall 2024. Responsibilities included course organization, student Q&A, experimental design, and grading assignments.

Teaching Assistant – Natural Language Processing (Spring 2025)

PhD-level course, Zhongguancun Academy, 2025

Served as a teaching assistant for the Natural Language Processing course offered by Professor Chengqing Zong and Professor Jiajun Zhang at the Zhongguancun Academy in Spring 2025. Responsibilities included course organization, student Q&A, and grading assignments.

Teaching Assistant – Practical Natural Language Processing (Fall 2025)

Undergraduate course, School of Artificial Intelligence, University of Chinese Academy of Sciences, 2025

Served as a teaching assistant for the course Practical Natural Language Processing offered by Associate Professor Yang Zhao at the School of Artificial Intelligence, University of Chinese Academy of Sciences in Fall 2025. Responsibilities included course organization, student Q&A, experimental design, and grading assignments.