Multimodal learned sparse retrieval for image suggestion
T Nguyen, M Hendriksen, A Yates - arXiv preprint arXiv:2402.07736, 2024 - arxiv.org
Learned Sparse Retrieval (LSR) is a group of neural methods designed to encode queries
and documents into sparse lexical vectors. These vectors can be efficiently indexed and …
and documents into sparse lexical vectors. These vectors can be efficiently indexed and …
Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective
We examine the brittleness of the image-text retrieval (ITR) evaluation pipeline with a focus
on concept granularity. We start by analyzing two common benchmarks, MS-COCO and …
on concept granularity. We start by analyzing two common benchmarks, MS-COCO and …
DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities
Learned Sparse Retrieval (LSR) models use vocabularies from pre-trained transformers,
which often split entities into nonsensical fragments. Splitting entities can reduce retrieval …
which often split entities into nonsensical fragments. Splitting entities can reduce retrieval …
Neural Lexical Search with Learned Sparse Retrieval
A Yates, C Lassance, S MacAvaney… - Proceedings of the 2024 …, 2024 - dl.acm.org
Learned Sparse Retrieval (LSR) techniques use neural machinery to represent queries and
documents as learned bags of words. In contrast with other neural retrieval techniques, such …
documents as learned bags of words. In contrast with other neural retrieval techniques, such …
Retrieval Evaluation for Long-Form and Knowledge-Intensive Image–Text Article Composition
This paper examines the integration of images into Wikipedia articles by evaluating image–
text retrieval tasks in multimedia content creation, focusing on developing retrieval …
text retrieval tasks in multimedia content creation, focusing on developing retrieval …