Copertina

Improving Rare Word Translation With Dictionaries and Attention Masking

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sible, Kenneth J., Chiang, David
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Using Source-Side Confidence Estimation for Reliable Translation into Unfamiliar Languages
di: Sible, Kenneth J., et al.
Pubblicazione: (2025)

Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
di: Yang, Andy, et al.
Pubblicazione: (2023)

DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
di: Maheshwari, Ayush, et al.
Pubblicazione: (2022)

Simulating Hard Attention Using Soft Attention
di: Yang, Andy, et al.
Pubblicazione: (2024)

SEA: Sparse Linear Attention with Estimated Attention Mask
di: Lee, Heejun, et al.
Pubblicazione: (2023)

Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
di: Wang, Junxuan, et al.
Pubblicazione: (2025)

Nostra Domina at EvaLatin 2024: Improving Latin Polarity Detection through Data Augmentation
di: Bothwell, Stephen, et al.
Pubblicazione: (2024)

Improving Word Translation via Two-Stage Contrastive Learning
di: Li, Yaoyiran, et al.
Pubblicazione: (2022)

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning
di: Olmo, Jeffrey, et al.
Pubblicazione: (2024)

The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrieval
di: Chiang, Ting-Rui, et al.
Pubblicazione: (2025)

Faster Transformer Decoding: N-gram Masked Self-Attention
di: Chelba, Ciprian, et al.
Pubblicazione: (2020)

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
di: Tian, Qiwei, et al.
Pubblicazione: (2025)

Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
di: Zhuang, Xialie, et al.
Pubblicazione: (2025)

Edeflip: Supervised Word Translation between English and Yoruba
di: Abioye, Ikeoluwa, et al.
Pubblicazione: (2025)

Trainable Dynamic Mask Sparse Attention
di: Shi, Jingze, et al.
Pubblicazione: (2025)

Efficiently Dispatching Flash Attention For Partially Filled Attention Masks
di: Sharma, Agniv, et al.
Pubblicazione: (2024)

Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
di: Zhussip, Magauiya, et al.
Pubblicazione: (2025)

Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation
di: Wu, Di, et al.
Pubblicazione: (2023)

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
di: Bombari, Simone, et al.
Pubblicazione: (2024)

Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation
di: Raffel, Matthew, et al.
Pubblicazione: (2024)

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

An Improved Deep Learning Model for Word Embeddings Based Clustering for Large Text Datasets
di: Sutrakar, Vijay Kumar, et al.
Pubblicazione: (2025)

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

Improving Transformers with Dynamically Composable Multi-Head Attention
di: Xiao, Da, et al.
Pubblicazione: (2024)

Self-Augmented In-Context Learning for Unsupervised Word Translation
di: Li, Yaoyiran, et al.
Pubblicazione: (2024)

Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling
di: Padole, Tejomay Kishor, et al.
Pubblicazione: (2025)

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
di: Lim, Sungjun, et al.
Pubblicazione: (2026)

LogicDiff: Logic-Guided Denoising Improves Zero-Shot Reasoning in Masked Diffusion Language Models
di: Aman, Shaik
Pubblicazione: (2026)

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
di: Chen, Changyu, et al.
Pubblicazione: (2024)

OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention
di: Zhou, Chenyu, et al.
Pubblicazione: (2026)

Selective Attention Improves Transformer
di: Leviathan, Yaniv, et al.
Pubblicazione: (2024)

SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection
di: Mou, Guanyi, et al.
Pubblicazione: (2024)

Transformers in Uniform TC$^0$
di: Chiang, David
Pubblicazione: (2024)

Wikipedia is Not a Dictionary, Delete! Text Classification as a Proxy for Analysing Wiki Deletion Discussions
di: Borkakoty, Hsuvas, et al.
Pubblicazione: (2025)

Counting Like Transformers: Compiling Temporal Counting Logic Into Softmax Transformers
di: Yang, Andy, et al.
Pubblicazione: (2024)

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
di: Gu, Zhuohan, et al.
Pubblicazione: (2024)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
di: Karvonen, Adam, et al.
Pubblicazione: (2024)

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
di: Zheng, Carolina, et al.
Pubblicazione: (2025)

Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text
di: Jarca, Andrei, et al.
Pubblicazione: (2025)

Low-Cost Generation and Evaluation of Dictionary Example Sentences
di: Cai, Bill, et al.
Pubblicazione: (2024)