Retrieving and reading: A comprehensive survey on open-domain question answering

F Zhu, W Lei, C Wang, J Zheng, S Poria… - arxiv preprint arxiv …, 2021‏ - arxiv.org
Open-domain Question Answering (OpenQA) is an important task in Natural Language
Processing (NLP), which aims to answer a question in the form of natural language based …

A survey on rag meeting llms: Towards retrieval-augmented large language models

W Fan, Y Ding, L Ning, S Wang, H Li, D Yin… - Proceedings of the 30th …, 2024‏ - dl.acm.org
As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can
offer reliable and up-to-date external knowledge, providing huge convenience for numerous …

[PDF][PDF] Dense Passage Retrieval for Open-Domain Question Answering.

V Karpukhin, B Oguz, S Min, PSH Lewis, L Wu… - EMNLP (1), 2020‏ - arxiv.org
Open-domain question answering relies on efficient passage retrieval to select candidate
contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de …

Retrieval augmented language model pre-training

K Guu, K Lee, Z Tung, P Pasupat… - … on machine learning, 2020‏ - proceedings.mlr.press
Abstract Language model pre-training has been shown to capture a surprising amount of
world knowledge, crucial for NLP tasks such as question answering. However, this …

Recommender systems based on graph embedding techniques: A review

Y Deng - IEEE Access, 2022‏ - ieeexplore.ieee.org
As a pivotal tool to alleviate the information overload problem, recommender systems aim to
predict user's preferred items from millions of candidates by analyzing observed user-item …

Open-domain visual entity recognition: Towards recognizing millions of wikipedia entities

H Hu, Y Luan, Y Chen, U Khandelwal… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong
generalization on various visual domains and tasks. However, existing image classification …

Collaborative metric learning

CK Hsieh, L Yang, Y Cui, TY Lin, S Belongie… - Proceedings of the 26th …, 2017‏ - dl.acm.org
Metric learning algorithms produce distance metrics that capture the important relationships
among data. In this work, we study the connection between metric learning and collaborative …

A^ 3: Accelerating attention mechanisms in neural networks with approximation

TJ Ham, SJ Jung, S Kim, YH Oh, Y Park… - … Symposium on High …, 2020‏ - ieeexplore.ieee.org
With the increasing computational demands of the neural networks, many hardware
accelerators for the neural networks have been proposed. Such existing neural network …

Semi-supervised learning for cross-domain recommendation to cold-start users

SK Kang, J Hwang, D Lee, H Yu - Proceedings of the 28th ACM …, 2019‏ - dl.acm.org
Providing accurate recommendations to newly joined users (or potential users, so-called
cold-start users) has remained a challenging yet important problem in recommender …

Entities as experts: Sparse memory access with entity supervision

T Févry, LB Soares, N FitzGerald, E Choi… - arxiv preprint arxiv …, 2020‏ - arxiv.org
We focus on the problem of capturing declarative knowledge about entities in the learned
parameters of a language model. We introduce a new model-Entities as Experts (EAE)-that …