Text Ranking and Classification using Data Compression
A well-known but rarely used approach to text categorization uses conditional entropy estimates computed using data compression tools. Text affinity scores derived from compressed sizes can be used for classification and ranking tasks, but their success depends on the compression tools used. We use the Zstandard compressor and strengthen these ideas in several ways, calling the resulting language-agnostic technique Zest. In applications, this approach simplifies configuration, avoiding careful feature extraction and large ML models. Our ablation studies confirm the value of individual enhancements we introduce. We show that Zest complements and can compete with language-specific multidimensional content embeddings in production, but cannot outperform other counting methods on public datasets.
Code (1)
Tasks
ClassificationData CompressionText CategorizationSimilar Papers 제목 키워드 기반
Approximating Human-Like Few-shot Learning with GPT-based Compression
In this work, we conceptualize the learning process as information compression. We seek to equip generative pre-trained models with human-like learning capabilities that enable data compression during inference. We prese…
Data CompressionFew-Shot LearningSemantic SimilaritySemantic Textual Similarity+4Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking
Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted…
QuantizationRe-RankingCompact Token Representations with Contextual Quantization for Efficient Document Re-ranking
Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopte…
QuantizationRe-RankingStock exchange shares ranking and binary-ternary compressive coding
This paper proposes a method for ranking the investment attractiveness of exchange-traded stocks where investment risk is not related to the volatility indicator but instead is related to the indicator of compression of …
Time SeriesTime Series AnalysisOSCAR: Online Soft Compression And Reranking
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge, leading to improved accuracy and relevance. However, scaling RAG pipelines remains computationally expensive a…
RAGRerankingRetrievalRetrieval-augmented Generation