paper-with-me

홈 › Papers

Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation

2023-05-02 · DongNyeong Heo, Heeyoul Choi

Non-autoregressive neural machine translation (NAT) offers substantial translation speed up compared to autoregressive neural machine translation (AT) at the cost of translation quality. Latent variable modeling has emerged as a promising approach to bridge this quality gap, particularly for addressing the chronic multimodality problem in NAT. In the previous works that used latent variable modeling, they added an auxiliary model to estimate the posterior distribution of the latent variable conditioned on the source and target sentences. However, it causes several disadvantages, such as redundant information extraction in the latent variable, increasing the number of parameters, and a tendency to ignore some information from the inputs. In this paper, we propose a novel latent variable modeling that integrates a dual reconstruction perspective and an advanced hierarchical latent modeling with a shared intermediate latent space across languages. This latent variable modeling hypothetically alleviates or prevents the above disadvantages. In our experiment results, we present comprehensive demonstrations that our proposed approach infers superior latent variables which lead better translation quality. Finally, in the benchmark translation tasks, such as WMT, we demonstrate that our proposed method significantly improves translation quality compared to previous NAT baselines including the state-of-the-art NAT model.

📄 PDF Abstract BibTeX arXiv:2305.03511

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Bilingual-GAN: A Step Towards Parallel Text Generation

2019-04-09 · WS 2019 6 · Ahmad Rashid, Alan Do-Omri, Md. Akmal Haidar, Qun Liu 외

Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose…

DecoderDenoisingMachine TranslationText Generation+2

Multivariate Scientific Data Compression with Learned Cross-Variable Latent Decorrelation and Autoregressive Entropy Modeling

2026-08-31 · Liangji Zhu, Anand Rangarajan, Sanjay Ranka arxiv

Scientific simulations generate collections of physical fields with heterogeneous statistics and dependencies, yet learned compressors often encode those fields independently or rely on a shared encoder without explicitl…

Understanding Cross-Lingual Inconsistency in Large Language Models

2025-05-19 · Zheng Wei Lim, Alham Fikri Aji, Trevor Cohn

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models a…

Cross-Lingual TransferTransfer Learning

Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

2024-10-16 · Yongxin Zhu, Bocheng Li, Hang Zhang, Xin Li 외

Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencod…

Conditional Image GenerationImage GenerationLinear-Probe ClassificationSelf-Supervised Image Classification+2

Text2Sign Diffusion: A Generative Approach for Gloss-Free Sign Language Production

2025-09-13 · Liqian Feng, Lintao Wang, Kun Hu, Dehui Kong 외 arxiv

Sign language production (SLP) aims to translate spoken language sentences into a sequence of pose frames in a sign language, bridging the communication gap and promoting digital inclusion for deaf and hard-of-hearing co…