paper-with-me

Papers

VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation

2022-01-20 · LREC 2022 6 · Yihang Li, Shuichiro Shimizu, Weiqi Gu, Chenhui Chu, Sadao Kurohashi

Existing multimodal machine translation (MMT) datasets consist of images and video captions or general subtitles, which rarely contain linguistic ambiguity, making visual information not so effective to generate appropriate translations. We introduce VISA, a new dataset that consists of 40k Japanese-English parallel sentence pairs and corresponding video clips with the following key features: (1) the parallel sentences are subtitles from movies and TV episodes; (2) the source subtitles are ambiguous, which means they have multiple possible translations with different meanings; (3) we divide the dataset into Polysemy and Omission according to the cause of ambiguity. We show that VISA is challenging for the latest MMT system, and we hope that the dataset can facilitate MMT research. The VISA dataset is available at: https://github.com/ku-nlp/VISA.

📄 PDF Abstract BibTeX arXiv:2201.08054

Code (1)

ku-nlp/visa 공식 구현

Tasks

Machine TranslationMultimodal Machine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

LaViSA: A Language and Vision Structural Ambiguity Benchmark

2026-06-17 · Lee Sangmyeong, Shun Inadumi, Koichiro Yoshino arxiv

Structural ambiguity arises when a single sentence admits multiple valid interpretations due to its syntactic structure, posing a fundamental challenge for language understanding. Visual scenes serve as useful cues for r…

Video-Helpful Multimodal Machine Translation

2023-10-31 · Yihang Li, Shuichiro Shimizu, Chenhui Chu, Sadao Kurohashi 외

Existing multimodal machine translation (MMT) datasets consist of images and video captions or instructional video subtitles, which rarely contain linguistic ambiguity, making visual information ineffective in generating…

Machine TranslationMultimodal Machine TranslationTranslation

Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing

2025-03-01 · CVPR 2025 1 · Yanjun Li, Zhaoyang Li, Honghui Chen, Lizhi Xu

Video Scene Graph Generation (VidSGG) aims to capture dynamic relationships among entities by sequentially analyzing video frames and integrating visual and semantic information. However, VidSGG is challenged by signific…

Graph GenerationScene Graph GenerationTripletVideo scene graph generation

VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation

2026-05-18 · Linan ZHU, Zihao Zhai, Xiao Han, Yuqian Fu 외 arxiv

Emotion Recognition in Conversation (ERC) is essential for effective human-machine interaction, aiming to identify speakers' emotional states in multi-turn dialogues. Early text-based methods struggle with complex scenar…

Emotion Recognition in ConversationComputational Efficiency

ViSaRL: Visual Reinforcement Learning Guided by Human Saliency

2024-03-16 · Anthony Liang, Jesse Thomason, Erdem Biyik

Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant informatio…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Manipulation