paper-with-me

Papers

Generative Imagination Elevates Machine Translation

2020-09-21 · NAACL 2021 4 · Quanyu Long, Mingxuan Wang, Lei LI

There are common semantics shared across text and images. Given a sentence in a source language, whether depicting the visual scene helps translation into a target language? Existing multimodal neural machine translation methods (MNMT) require triplets of bilingual sentence - image for training and tuples of source sentence - image for inference. In this paper, we propose ImagiT, a novel machine translation method via visual imagination. ImagiT first learns to generate visual representation from the source sentence, and then utilizes both source sentence and the "imagined representation" to produce a target translation. Unlike previous methods, it only needs the source sentence at the inference time. Experiments demonstrate that ImagiT benefits from visual imagination and significantly outperforms the text-only neural machine translation baselines. Further analysis reveals that the imagination process in ImagiT helps fill in missing information when performing the degradation strategy.

📄 PDF Abstract BibTeX arXiv:2009.09654

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationMultimodal Machine TranslationSentenceTransfer LearningTranslation

Similar Papers 제목 키워드 기반

Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation

2024-12-17 · Andong Chen, Yuchen Song, Kehai Chen, Muyun Yang 외

Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations.…

Language ModelingLanguage ModellingLarge Language ModelMachine Translation+3

Autocorrect in the Process of Translation --- Multi-task Learning Improves Dialogue Machine Translation

2021-06-01 · NAACL 2021 4 · Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI 외

Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep anal…

Machine TranslationMulti-Task LearningTranslation

Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation

2021-03-30 · Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI 외

Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep anal…

Machine TranslationMulti-Task LearningTranslation

PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics

2026-05-18 · Xueyu Luan, Chenwei Shi arxiv

World models built on recurrent state space architectures enable efficient latent imagination, yet remain physically unstructured, producing dynamics that violate conservation and dissipative principles. We introduce a u…

Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination

2023-11-11 · Lu Wen, Songan Zhang, H. Eric Tseng, Huei Peng

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-tr…

Meta Reinforcement Learning