Papers with Code 아카이브
Text Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
TokAlign: Efficient Vocabulary Adaptation via Token Alignment
Beyond Text Compression: Evaluating Tokenizers Across Scales
Measuring Information Distortion in Hierarchical Ultra long Novel Generation:The Optimal Expansion Ratio
Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method
Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction
Text Compression for Efficient Language Generation
Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches
Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance
L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression
An Enhanced Text Compression Approach Using Transformer-based Language Models
IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model
FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
AlphaZip: Neural Network-Enhanced Lossless Text Compression
BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training
Recurrent Context Compression: Efficiently Expanding the Context Window of LLM
Variational Bayesian Methods for a Tree-Structured Stick-Breaking Process Mixture of Gaussians by Application of the Bayes Codes for Context Tree Models
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance
Neural Retrievers are Biased Towards LLM-Generated Content
Semantic Text Compression for Classification
EntropyRank: Unsupervised Keyphrase Extraction via Side-Information Optimization for Language Model-based Text Compression
Approximating Human-Like Few-shot Learning with GPT-based Compression
Gzip versus bag-of-words for text classification
LLMZip: Lossless Text Compression using Large Language Models
Optimal alphabet for single text compression
Contextualized Semantic Distance between Highly Overlapped Texts
Text Compression-aided Transformer Encoding
Machine Translation with Unsupervised Length-Constraints
Deleter: Leveraging BERT to Perform Unsupervised Successive Text Compression
A study for Image compression using Re-Pair algorithm
Text Compression for Sentiment Analysis via Evolutionary Algorithms
A Neural Network Approach for Mixing Language Models
Long-Short Range Context Neural Networks for Language Modeling
A Batch Noise Contrastive Estimation Approach for Training Large Vocabulary Language Models
Authorship Verification based on Compression-Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.