paper-with-me

홈 › Papers

Translation in the Wild

2025-05-29 · Yuri Balashov

Large Language Models (LLMs) excel in translation among other things, demonstrating competitive performance for many language pairs in zero- and few-shot settings. But unlike dedicated neural machine translation models, LLMs are not trained on any translation-related objective. What explains their remarkable translation abilities? Are these abilities grounded in "incidental bilingualism" (Briakou et al. 2023) in training data? Does instruction tuning contribute to it? Are LLMs capable of aligning and leveraging semantically identical or similar monolingual contents from different corners of the internet that are unlikely to fit in a single context window? I offer some reflections on this topic, informed by recent studies and growing user experience. My working hypothesis is that LLMs' translation abilities originate in two different types of pre-training data that may be internalized by the models in different ways. I discuss the prospects for testing the "duality" hypothesis empirically and its implications for reconceptualizing translation, human and machine, in the age of deep learning.

📄 PDF Abstract BibTeX arXiv:2505.23548

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models

2023-11-20 · Pooya Fayyazsanavi, Negar Nejatishahidin, Jana Kosecka

We address the task of American Sign Language fingerspelling translation using videos in the wild. We exploit advances in more accurate hand pose estimation and propose a novel architecture that leverages the transformer…

DecoderHand Pose EstimationLanguage ModelingLanguage Modelling+4

Unpaired Photo-to-Caricature Translation on Faces in the Wild

2017-11-29 · Ziqiang Zheng, Wang Chao, Zhibin Yu, Nan Wang 외

Recently, image-to-image translation has been made much progress owing to the success of conditional Generative Adversarial Networks (cGANs). And some unpaired methods based on cycle consistency loss such as DualGAN, Cyc…

CaricatureImage-to-Image TranslationPhoto-To-Caricature TranslationRepresentation Learning+1

Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps

2019-07-12 · Yahui Liu, Marco De Nadai, Gloria Zen, Nicu Sebe 외

Recent works have shown Generative Adversarial Networks (GANs) to be particularly effective in image-to-image translations. However, in tasks such as body pose and hand gesture translation, existing methods usually requi…

Gesture-to-Gesture TranslationTranslation

Semi-Supervised Domain Adaptation for Wildfire Detection

2024-04-02 · Jooyoung Jang, Youngseo Cha, Jisu Kim, SooHyung Lee 외

Recently, both the frequency and intensity of wildfires have increased worldwide, primarily due to climate change. In this paper, we propose a novel protocol for wildfire detection, leveraging semi-supervised Domain Adap…

Domain Adaptationobject-detectionObject DetectionSemi-supervised Domain Adaptation

Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild

2023-03-23 · CVPR 2023 1 · Gyeongsik Moon

Despite recent achievements, existing 3D interacting hands recovery methods have shown results mainly on motion capture (MoCap) environments, not on in-the-wild (ITW) ones. This is because collecting 3D interacting hands…