paper-with-me

Papers

Text Ranking and Classification using Data Compression

2021-09-23 · NeurIPS Workshop ICBINB 2021 12 · Nitya Kasturi, Igor L. Markov

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.

📄 PDF Abstract BibTeX arXiv:2109.11577

Code (1)

facebookresearch/zest 공식 구현

Tasks

ClassificationData CompressionText Categorization

Similar Papers 제목 키워드 기반

Approximating Human-Like Few-shot Learning with GPT-based Compression

2023-08-14 · Cynthia Huang, Yuqing Xie, Zhiying Jiang, Jimmy Lin 외

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+4

Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking

2022-03-29 · ACL 2022 5 · Yingrui Yang, Yifan Qiao, Tao Yang

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-Ranking

Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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-Ranking

Stock exchange shares ranking and binary-ternary compressive coding

2021-10-20 · Igor Nesiolovskiy

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 Analysis

OSCAR: Online Soft Compression And Reranking

2025-03-17 · Maxime Louis, Thibault Formal, Hervé Dejean, Stéphane Clinchant

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