paper-with-me

Papers

Flexible retrieval with NMSLIB and FlexNeuART

2020-10-28 · EMNLP (NLPOSS) 2020 11 · Leonid Boytsov, Eric Nyberg

Our objective is to introduce to the NLP community an existing k-NN search library NMSLIB, a new retrieval toolkit FlexNeuART, as well as their integration capabilities. NMSLIB, while being one the fastest k-NN search libraries, is quite generic and supports a variety of distance/similarity functions. Because the library relies on the distance-based structure-agnostic algorithms, it can be further extended by adding new distances. FlexNeuART is a modular, extendible and flexible toolkit for candidate generation in IR and QA applications, which supports mixing of classic and neural ranking signals. FlexNeuART can efficiently retrieve mixed dense and sparse representations (with weights learned from training data), which is achieved by extending NMSLIB. In that, other retrieval systems work with purely sparse representations (e.g., Lucene), purely dense representations (e.g., FAISS and Annoy), or only perform mixing at the re-ranking stage.

📄 PDF Abstract BibTeX arXiv:2010.14848

Code (2)

oaqa/FlexNeuART 공식 구현 pytorch
oaqa/knn4qa pytorch

Tasks

Re-RankingRetrieval

Methods 이 논문이 사용한 방법론

k-NN $k$-Nearest Neighbors is a clustering-based algorithm for classification and regression. It is a a type of instance-based learning as it does not attempt to construct a…

Similar Papers 제목 키워드 기반

Non-Metric Space Library Manual

2015-08-22 · Bilegsaikhan Naidan, Leonid Boytsov, Yury Malkov, David Novak

This document covers a library for fast similarity (k-NN)search. It describes only search methods and distances (spaces). Details about building, installing, Python bindings can be found online:https://github.com/searchi…

Deep Learning-based Online Alternative Product Recommendations at Scale

2021-04-15 · WS 2020 7 · Mingming Guo, Nian Yan, Xiquan Cui, San He Wu 외

Alternative recommender systems are critical for ecommerce companies. They guide customers to explore a massive product catalog and assist customers to find the right products among an overwhelming number of options. How…

Deep LearningRecommendation Systems

Towards Dynamic Dense Retrieval with Routing Strategy

2026-02-26 · Zhan Su, Fengran Mo, Jinghan Zhang, Yuchen Hui 외 arxiv

The \textit{de facto} paradigm for applying dense retrieval (DR) to new tasks involves fine-tuning a pre-trained model for a specific task. However, this paradigm has two significant limitations: (1) It is difficult adap…

Domain Adaptation

Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval

2026-04-07 · Yuxin Yang, Yinan Zhou, Yuxin Chen, Ziqi Zhang 외 arxiv

Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inherently prioritizes semantic matching, s…

Image Retrieval

Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval

2022-03-11 · Luyu Gao, Xueguang Ma, Jimmy Lin, Jamie Callan

Recent rapid advancements in deep pre-trained language models and the introductions of large datasets have powered research in embedding-based dense retrieval. While several good research papers have emerged, many of the…

GPURetrieval