Retrieval-Enhanced Machine Learning

05/02/2022
by   Hamed Zamani, et al.
0

Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models. In this way, the core principles of indexing, representation, retrieval, and ranking can be applied and extended to substantially improve model generalization, scalability, robustness, and interpretability. We describe a generic retrieval-enhanced machine learning (REML) framework, which includes a number of existing models as special cases. REML challenges information retrieval conventions, presenting opportunities for novel advances in core areas, including optimization. The REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/04/2022

Explainable Information Retrieval: A Survey

Explainable information retrieval is an emerging research area aiming to...
research
02/23/2021

Neural Ranking Models for Document Retrieval

Ranking models are the main components of information retrieval systems....
research
04/26/2023

A Personalized Dense Retrieval Framework for Unified Information Access

Developing a universal model that can efficiently and effectively respon...
research
05/01/2022

Can Information Behaviour Inform Machine Learning?

The objective of this paper is to explore the opportunities for human in...
research
07/24/2023

RRAML: Reinforced Retrieval Augmented Machine Learning

The emergence of large language models (LLMs) has revolutionized machine...
research
03/27/2013

Machine Learning, Clustering, and Polymorphy

This paper describes a machine induction program (WITT) that attempts to...
research
09/16/2022

Interactions in Information Spread

Since the development of writing 5000 years ago, human-generated data ge...

Please sign up or login with your details

Forgot password? Click here to reset