Copertina

Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Forrester, Chris, Sulea, Octavia
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring Prompt-Based Methods for Zero-Shot Hypernym Prediction with Large Language Models
di: Tikhomirov, Mikhail, et al.
Pubblicazione: (2024)

SHADE: Semantic Hypernym Annotator for Domain-specific Entities -- DnD Domain Use Case
di: Peiris, Akila, et al.
Pubblicazione: (2024)

Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet
di: Augello, Lorenzo, et al.
Pubblicazione: (2025)

HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings
di: Parmar, Maulik, et al.
Pubblicazione: (2022)

Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy
di: Malashin, Roman, et al.
Pubblicazione: (2025)

On the Semantic and Syntactic Information Encoded in Proto-Tokens for One-Step Text Reconstruction
di: Bondarenko, Ivan, et al.
Pubblicazione: (2026)

Beyond Text Compression: Evaluating Tokenizers Across Scales
di: Lotz, Jonas F., et al.
Pubblicazione: (2025)

Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics
di: R V, Kavin, et al.
Pubblicazione: (2025)

Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction
di: Zou, Yuchun, et al.
Pubblicazione: (2026)

KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
di: Yuan, Aomufei, et al.
Pubblicazione: (2025)

See the Text: From Tokenization to Visual Reading
di: Xing, Ling, et al.
Pubblicazione: (2025)

Greed is All You Need: An Evaluation of Tokenizer Inference Methods
di: Uzan, Omri, et al.
Pubblicazione: (2024)

From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction
di: Zhu, Mingcheng, et al.
Pubblicazione: (2026)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
di: Kim, Eunji, et al.
Pubblicazione: (2024)

Tokenization Is More Than Compression
di: Schmidt, Craig W., et al.
Pubblicazione: (2024)

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation
di: Lin, Xiaolin, et al.
Pubblicazione: (2025)

Learning to Compress Prompts with Gist Tokens
di: Mu, Jesse, et al.
Pubblicazione: (2023)

ACT-MNMT Auto-Constriction Turning for Multilingual Neural Machine Translation
di: Dai, Shaojie, et al.
Pubblicazione: (2024)

Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance
di: Goldman, Omer, et al.
Pubblicazione: (2024)

Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction
di: Mao, Yu, et al.
Pubblicazione: (2025)

zip2zip: Inference-Time Adaptive Tokenization via Online Compression
di: Geng, Saibo, et al.
Pubblicazione: (2025)

Frequency-Ordered Tokenization for Better Text Compression
di: Kalcher, Maximilian
Pubblicazione: (2026)

Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations
di: Zhao, Yize, et al.
Pubblicazione: (2025)

LLM-Augmented Semantic Steering of Text Embedding Projection Spaces
di: Liu, Wei, et al.
Pubblicazione: (2026)

Brain-CLIPLM: Decoding Compressed Semantic Representations in EEG for Language Reconstruction
di: Yang, Xiaoli, et al.
Pubblicazione: (2026)

Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation
di: Moroni, Luca, et al.
Pubblicazione: (2025)

Faster Superword Tokenization
di: Schmidt, Craig W., et al.
Pubblicazione: (2026)

From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution
di: Chizhov, Pavel, et al.
Pubblicazione: (2026)

Morphologically-Informed Tokenizers for Languages with Non-Concatenative Morphology: A case study of Yoloxóchtil Mixtec ASR
di: Crawford, Chris
Pubblicazione: (2025)

SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors
di: Trukhina, Natalia, et al.
Pubblicazione: (2026)

Multi-word Tokenization for Sequence Compression
di: Gee, Leonidas, et al.
Pubblicazione: (2024)

Text2Token: Unsupervised Text Representation Learning with Token Target Prediction
di: An, Ruize, et al.
Pubblicazione: (2025)

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
di: Shani, Chen, et al.
Pubblicazione: (2025)

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
di: Song, Yuhan, et al.
Pubblicazione: (2025)

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
di: Zhang, Jiebin, et al.
Pubblicazione: (2024)

Lossless Token Sequence Compression via Meta-Tokens
di: Harvill, John, et al.
Pubblicazione: (2025)

Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation
di: Belikova, Julia, et al.
Pubblicazione: (2026)

Text Compression for Efficient Language Generation
di: Gu, David, et al.
Pubblicazione: (2025)

A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens
di: Nie, Zhijie, et al.
Pubblicazione: (2024)

Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens
di: Manakul, Potsawee, et al.
Pubblicazione: (2026)