Imagen de Portada

The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tokarchuk, Evgeniia, Niculae, Vlad
Formato:	Preprint
Publicado:	2023
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Angular Dispersion Accelerates $k$-Nearest Neighbors Machine Translation
por: Tokarchuk, Evgeniia, et al.
Publicado: (2025)

Representation Collapse in Machine Translation Through the Lens of Angular Dispersion
por: Tokarchuk, Evgeniia, et al.
Publicado: (2026)

Keep your distance: learning dispersed embeddings on $\mathbb{S}_m$
por: Tokarchuk, Evgeniia, et al.
Publicado: (2025)

Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
por: Troshin, Sergey, et al.
Publicado: (2025)

The Unreasonable Effectiveness of Eccentric Automatic Prompts
por: Battle, Rick, et al.
Publicado: (2024)

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
por: Hase, Peter, et al.
Publicado: (2024)

Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation
por: Mohammed, Wafaa, et al.
Publicado: (2024)

The Unreasonable Ineffectiveness of the Deeper Layers
por: Gromov, Andrey, et al.
Publicado: (2024)

AdaSplash-2: Faster Differentiable Sparse Attention
por: Gonçalves, Nuno, et al.
Publicado: (2026)

Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
por: Mohammed, Wafaa, et al.
Publicado: (2025)

Self-generated Replay Memories for Continual Neural Machine Translation
por: Resta, Michele, et al.
Publicado: (2024)

The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs
por: Bandarkar, Lucas, et al.
Publicado: (2025)

Self-Vocabularizing Training for Neural Machine Translation
por: Lin, Pin-Jie, et al.
Publicado: (2025)

Conditioning LLMs with Emotion in Neural Machine Translation
por: Brazier, Charles, et al.
Publicado: (2024)

The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
por: Donghi, Giovanni, et al.
Publicado: (2025)

On Measuring Context Utilization in Document-Level MT Systems
por: Mohammed, Wafaa, et al.
Publicado: (2024)

To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation
por: Azeemi, Abdul Hameed, et al.
Publicado: (2024)

Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translation
por: Emezue, Chris
Publicado: (2024)

An In-depth Walkthrough on Evolution of Neural Machine Translation
por: Jagtap, Rohan, et al.
Publicado: (2020)

Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation
por: Heo, DongNyeong, et al.
Publicado: (2023)

Attention Sinks in Massively Multilingual Neural Machine Translation:Discovery, Analysis, and Mitigation
por: Mutisya, Hillary, et al.
Publicado: (2026)

From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation
por: Marashian, Ali, et al.
Publicado: (2024)

Understanding Token Probability Encoding in Output Embeddings
por: Cho, Hakaze, et al.
Publicado: (2024)

Output Embedding Centering for Stable LLM Pretraining
por: Stollenwerk, Felix, et al.
Publicado: (2026)

Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation
por: Meng, Yan, et al.
Publicado: (2024)

Simple and Effective Input Reformulations for Translation
por: Yu, Brian, et al.
Publicado: (2023)

Curated Datasets and Neural Models for Machine Translation of Informal Registers between Mayan and Spanish Vernaculars
por: Lou, Andrés, et al.
Publicado: (2024)

Integrating Pre-trained Language Model into Neural Machine Translation
por: Hwang, Soon-Jae, et al.
Publicado: (2023)

Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model
por: García-Romero, Cristian, et al.
Publicado: (2025)

Ensemble Self-Training for Unsupervised Machine Translation
por: Aharon, Ido, et al.
Publicado: (2026)

Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages
por: Chen, Danlu, et al.
Publicado: (2026)

Usefulness of Emotional Prosody in Neural Machine Translation
por: Brazier, Charles, et al.
Publicado: (2024)

On the Low-Rank Parametrization of Reward Models for Controlled Language Generation
por: Troshin, Sergey, et al.
Publicado: (2024)

On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms
por: Yue, Richard, et al.
Publicado: (2024)

The Unreasonable Effectiveness of Solving Inverse Problems with Neural Networks
por: Holl, Philipp, et al.
Publicado: (2024)

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation
por: Wang, Yiming, et al.
Publicado: (2024)

Towards Explainable Evaluation Metrics for Machine Translation
por: Leiter, Christoph, et al.
Publicado: (2023)

QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
por: Faria, Gonçalo R. A., et al.
Publicado: (2024)

Life Cycle-Aware Evaluation of Knowledge Distillation for Machine Translation: Environmental Impact and Translation Quality Trade-offs
por: Attieh, Joseph, et al.
Publicado: (2026)

kNN For Whisper And Its Effect On Bias And Speaker Adaptation
por: Nachesa, Maya K., et al.
Publicado: (2024)