paper-with-me

Papers

ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation

2023-03-11 · Bang Yang, Fenglin Liu, Yuexian Zou, Xian Wu, YaoWei Wang, David A. Clifton

Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of labeled data are often not available. To relax the dependency on labeled data of downstream tasks, we propose an intuitive and effective zero-shot learning framework, ZeroNLG, which can deal with multiple NLG tasks, including image-to-text (image captioning), video-to-text (video captioning), and text-to-text (neural machine translation), across English, Chinese, German, and French within a unified framework. ZeroNLG does not require any labeled downstream pairs for training. During training, ZeroNLG (i) projects different domains (across modalities and languages) to corresponding coordinates in a shared common latent space; (ii) bridges different domains by aligning their corresponding coordinates in this space; and (iii) builds an unsupervised multilingual auto-encoder to learn to generate text by reconstructing the input text given its coordinate in shared latent space. Consequently, during inference, based on the data-to-text pipeline, ZeroNLG can generate target sentences across different languages given the coordinate of input data in the common space. Within this unified framework, given visual (imaging or video) data as input, ZeroNLG can perform zero-shot visual captioning; given textual sentences as input, ZeroNLG can perform zero-shot machine translation. We present the results of extensive experiments on twelve NLG tasks, showing that, without using any labeled downstream pairs for training, ZeroNLG generates high-quality and believable outputs and significantly outperforms existing zero-shot methods.

📄 PDF Abstract BibTeX arXiv:2303.06458

Code (2)

yangbang18/zeronlg 공식 구현 pytorch
yangbang18/clfm pytorch

Tasks

Image CaptioningImage to textMachine TranslationText GenerationTranslationVideo CaptioningZero-Shot LearningZero-Shot Machine Translation

Similar Papers 제목 키워드 기반

Enabling Small Models for Zero-Shot Selection and Reuse through Model Label Learning

2024-08-21 · Jia Zhang, Zhi Zhou, Lan-Zhe Guo, Yu-Feng Li

Vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot ability in image classification tasks by aligning text and images but suffer inferior performance compared with task-specific expert models. …

image-classificationImage ClassificationZero-Shot Learning

PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder

2026-06-01 · Yancheng Liu, Kenichi Maeda, Manan Pancholy arxiv

Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data. We present PaCX-MAE, a cross-modal distillation framework that injects physiolo…

ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF

2023-08-11 · Victor Gallego

In this work, we address the problem of directing the text generation of a language model (LM) towards a desired behavior, aligning the generated text with the preferences of the human operator. We propose using another,…

AttributeDiversityLanguage ModelingLanguage Modelling+1

Zero-Shot Fact Verification via Natural Logic and Large Language Models

2024-10-04 · Marek Strong, Rami Aly, Andreas Vlachos

The recent development of fact verification systems with natural logic has enhanced their explainability by aligning claims with evidence through set-theoretic operators, providing faithful justifications. Despite these …

Fact VerificationZero-shot Generalization

Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization

2023-11-02 · NeurIPS 2023 11 · Jameel Hassan, Hanan Gani, Noor Hussein, Muhammad Uzair Khattak 외

The promising zero-shot generalization of vision-language models such as CLIP has led to their adoption using prompt learning for numerous downstream tasks. Previous works have shown test-time prompt tuning using entropy…

Domain GeneralizationPrompt LearningZero-shot Generalization