paper-with-me

Papers

Improved Learned Sparse Retrieval with Corpus-Specific Vocabularies

2024-01-12 · Puxuan Yu, Antonio Mallia, Matthias Petri

We explore leveraging corpus-specific vocabularies that improve both efficiency and effectiveness of learned sparse retrieval systems. We find that pre-training the underlying BERT model on the target corpus, specifically targeting different vocabulary sizes incorporated into the document expansion process, improves retrieval quality by up to 12% while in some scenarios decreasing latency by up to 50%. Our experiments show that adopting corpus-specific vocabulary and increasing vocabulary size decreases average postings list length which in turn reduces latency. Ablation studies show interesting interactions between custom vocabularies, document expansion techniques, and sparsification objectives of sparse models. Both effectiveness and efficiency improvements transfer to different retrieval approaches such as uniCOIL and SPLADE and offer a simple yet effective approach to providing new efficiency-effectiveness trade-offs for learned sparse retrieval systems.

📄 PDF Abstract BibTeX arXiv:2401.06703

Code (1)

pxyu/csv-for-lsr-ecir24 공식 구현 pytorch

Tasks

Retrieval

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Mistral-SPLADE: LLMs for better Learned Sparse Retrieval

2024-08-20 · Meet Doshi, Vishwajeet Kumar, Rudra Murthy, Vignesh P 외

Learned Sparse Retrievers (LSR) have evolved into an effective retrieval strategy that can bridge the gap between traditional keyword-based sparse retrievers and embedding-based dense retrievers. At its core, learned spa…

DecoderLanguage ModelingLanguage ModellingLarge Language Model+3

Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval

2023-05-12 · Iain Mackie, Shubham Chatterjee, Jeffrey Dalton

Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance feedback (GRF) shows that query expansi…

Document RankingRetrieval

Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval

2020-07-01 · ICLR 2021 1 · Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang 외

Conducting text retrieval in a dense learned representation space has many intriguing advantages over sparse retrieval. Yet the effectiveness of dense retrieval (DR) often requires combination with sparse retrieval. In t…

Contrastive LearningPassage RetrievalRerankingRetrieval+2

Faster Learned Sparse Retrieval with Block-Max Pruning

2024-05-02 · Antonio Mallia, Torten Suel, Nicola Tonellotto

Learned sparse retrieval systems aim to combine the effectiveness of contextualized language models with the scalability of conventional data structures such as inverted indexes. Nevertheless, the indexes generated by th…

Retrieval

Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

2022-01-14 · Shitao Xiao, Zheng Liu, Weihao Han, Jianjin Zhang 외

Ad-hoc search calls for the selection of appropriate answers from a massive-scale corpus. Nowadays, the embedding-based retrieval (EBR) becomes a promising solution, where deep learning based document representation and …

QuantizationRetrieval