No article text was recorded for this version.
dynamic vocabulary pruning
Version 1 of 150 papers65 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Sockeye Neural Machine Translation Toolkit at AMTA 2018
- Blog: Vocabulary Manipulation for Neural Machine Translation
- Blog: Neural Response Generation With Dynamic Vocabularies
- Blog: Enabling Real-time Neural IME with Incremental Vocabulary Selection
- Blog: DVAGen: Dynamic Vocabulary Augmented Generation
- Blog: OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU
- Blog: Neural Machine Translation with Word Predictions
- Blog: SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
- Blog: Efficient and High-Quality Neural Machine Translation with OpenNMT
- Blog: Improved beam search with constrained softmax for NMT
- Blog: A Configurable Multilingual Model is All You Need to Recognize All Languages
- Blog: On Using Very Large Target Vocabulary for Neural Machine Translation
- Blog: Efficient Inference for Multilingual Neural Machine Translation
- Blog: Fast Word Predictor for On-Device Application
- Blog: CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling
- Blog: Towards Compact and Fast Neural Machine Translation Using a Combined Method
- Blog: NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context Vocabularies
- Blog: Open Vocabulary Learning for Neural Chinese Pinyin IME
- Blog: Extra large vocabulary continuous speech recognition algorithm based on information retrieval
- Blog: Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling
- Blog: RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
- Blog: PAM: Understanding Product Images in Cross Product Category Attribute Extraction
- Blog: Scaling the Vocabulary of Non-autoregressive Models for Efficient Generative Retrieval
- Blog: A multi-pass, dynamic-vocabulary approach to real-time, large-vocabulary speech recognition
- Blog: Cue-word Driven Neural Response Generation with a Shrinking Vocabulary
- Blog: Vocabulary Manipulation for Neural Machine Translation
- Blog: A Classification Approach to Word Prediction
- Blog: Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks
- Blog: Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU
- Blog: XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
- Blog: Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
- Blog: BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models
- Blog: Word Completion- A First Step Toward Target-Text Mediated IMT
- Blog: FUDGE: Controlled Text Generation With Future Discriminators
- Blog: Joint Copying and Restricted Generation for Paraphrase
- Blog: Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks
- Blog: Open Vocabulary Learning for Neural Chinese Pinyin IME
- Blog: UNRAVEL - A Decipherment Toolkit
- Blog: Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
- Blog: Neural Machine Translation with Word Predictions
- Blog: TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
- Blog: Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
- Blog: Attention-based Vocabulary Selection for NMT Decoding
- Blog: Sequence-to-Lattice Models for Fast Translation
- Blog: Source-Language Entailment Modeling for Translating Unknown Terms
- Blog: Integrating bilingual lexicons in a probabilistic translation assistant
- Blog: DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities
- Blog: Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
- Blog: Image Captioning with Word Gate and Adaptive Self-Critical Learning
- Blog: Findings of the Second Workshop on Neural Machine Translation and Generation
History & citation
Current · Permanent link
- This direction split from Dynamic Vocabulary Selection for Efficient Neural Generation (88% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_dynamic_vocabulary_pruning_6ead2794,
title = {dynamic vocabulary pruning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dynamic-vocabulary-pruning/rdr_6ead279490df45038dcf9dea8f272462},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_dynamic_vocabulary_pruning_6ead2794_v1,
title = {dynamic vocabulary pruning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dynamic-vocabulary-pruning/rdr_6ead279490df45038dcf9dea8f272462/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}