Text Compression
17 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Text Compression
Most implemented papers
LLMZip: Lossless Text Compression using Large Language Models
We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens.
Neural Retrievers are Biased Towards LLM-Generated Content
Surprisingly, our findings indicate that neural retrieval models tend to rank LLM-generated documents higher.
Syntactically Informed Text Compression with Recurrent Neural Networks
We present a self-contained system for constructing natural language models for use in text compression.
Authorship Verification based on Compression-Models
Instead, the only three key components of our method are a compressing algorithm, a dissimilarity measure and a threshold, needed to accept or reject the authorship of the questioned document.
A Batch Noise Contrastive Estimation Approach for Training Large Vocabulary Language Models
Training large vocabulary Neural Network Language Models (NNLMs) is a difficult task due to the explicit requirement of the output layer normalization, which typically involves the evaluation of the full softmax function over the complete vocabulary.
Data-efficient Neural Text Compression with Interactive Learning
UKPLab/NAACL2019-interactiveCompression
•
•
NAACL 2019
Neural sequence-to-sequence models have been successfully applied to text compression.
Contextualized Semantic Distance between Highly Overlapped Texts
Stareru/NeighboringDistributionDivergence
•
•
Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation.
Gzip versus bag-of-words for text classification
The effectiveness of compression in text classification ('gzip') has recently garnered lots of attention.
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Additionally, our model is 3x-6x faster than existing prompt compression methods, while accelerating the end-to-end latency by 1. 6x-2. 9x with compression ratios of 2x-5x.
Recurrent Context Compression: Efficiently Expanding the Context Window of LLM
To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity.
