paper-with-me

홈 › Papers

Target Conditioning for One-to-Many Generation

2020-09-21 · Findings of the Association for Computational Linguistics 2020 · Marie-Anne Lachaux, Armand Joulin, Guillaume Lample

Neural Machine Translation (NMT) models often lack diversity in their generated translations, even when paired with search algorithm, like beam search. A challenge is that the diversity in translations are caused by the variability in the target language, and cannot be inferred from the source sentence alone. In this paper, we propose to explicitly model this one-to-many mapping by conditioning the decoder of a NMT model on a latent variable that represents the domain of target sentences. The domain is a discrete variable generated by a target encoder that is jointly trained with the NMT model. The predicted domain of target sentences are given as input to the decoder during training. At inference, we can generate diverse translations by decoding with different domains. Unlike our strongest baseline (Shen et al., 2019), our method can scale to any number of domains without affecting the performance or the training time. We assess the quality and diversity of translations generated by our model with several metrics, on three different datasets.

📄 PDF Abstract BibTeX arXiv:2009.09758

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderDiversityMachine TranslationNMTSentenceTranslation

Similar Papers 제목 키워드 기반

A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models

2026-08-19 · Libo Chen, Souvik Ghosh, Teo Deveney, Chris Budd 외 arxiv

We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at infere…

Conditional Image Generation

Auditing and Enforcing Conditional Fairness via Optimal Transport

2024-10-17 · Mohsen Ghassemi, Alan Mishler, Niccolo Dalmasso, Luhao Zhang 외

Conditional demographic parity (CDP) is a measure of the demographic parity of a predictive model or decision process when conditioning on an additional feature or set of features. Many algorithmic fairness techniques ex…

Fairness

VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation

2026-06-19 · Xuan Qi, Daniele Berardini, Dario Serez, Vito Paolo Pastore 외 arxiv

Unsupervised domain adaptation (UDA) aims to learn a target-domain classifier from labeled source data and unlabeled target data under distribution shift. Recent diffusion-based UDA methods approach this problem by synth…

Unsupervised Domain Adaptation

Decoupled Action Expert: Confining Task Knowledge to the Conditioning Pathway

2025-11-15 · Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li 외 arxiv

Many recent Vision-Language-Action models employ diffusion or flow-matching backbones with hundreds of millions of parameters for action generation. However, unlike image synthesis where the output spans millions of dive…

Vorch-Omni: Multi-Task Orchestration of Sight and Sound

2026-08-06 · Vorch Team, Xiaoyu Chen, Yang Ding, Cong Han 외 arxiv

Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must…