BM25 Query Augmentation Learned End-to-End
Given BM25's enduring competitiveness as an information retrieval baseline, we investigate to what extent it can be even further improved by augmenting and re-weighting its sparse query-vector representation. We propose an approach to learning an augmentation and a re-weighting end-to-end, and we find that our approach improves performance over BM25 while retaining its speed. We furthermore find that the learned augmentations and re-weightings transfer well to unseen datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalRetrievalZero Shot on BEIR (Inference Free Model)Similar Papers 제목 키워드 기반
Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga
We tackle one-shot object detection in Japanese Manga. The rising global popularity of Japanese manga has made the object detection of character faces increasingly important, with potential applications such as automatic…
ColorizationData AugmentationObjectobject-detection+2Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation
Query augmentation makes queries more meaningful by appending further information to the queries to find relevant documents. Current studies have proposed Large Language Model (LLM)-based embedders, which learn represent…
Query Augmentation by Decoding Semantics from Brain Signals
Query augmentation is a crucial technique for refining semantically imprecise queries. Traditionally, query augmentation relies on extracting information from initially retrieved, potentially relevant documents. If the q…
Document RankingNeuro-Symbolic Ontology-Mediated Query Answering
Recently, low-dimensional vector space representations of Knowledge Graphs (KGs) have been applied to find answers to logical queries over incomplete KGs. However, the current methods only focus on inductive reasoning, i…
Data AugmentationKnowledge GraphsThe Coverage Illusion: From Pre-retrieval Routing Failure to Post-retrieval Cascades in a Production RAG System
In modern RAG pipelines, query augmentation methods such as HyDE and query expansion are applied to every query, resulting in substantial LLM inference costs and increased end-to-end latency. The empirical justification …