Boosting Search Engines with Interactive Agents

09/01/2021
by   Leonard Adolphs, et al.
83

Can machines learn to use a search engine as an interactive tool for finding information? That would have far reaching consequences for making the world's knowledge more accessible. This paper presents first steps in designing agents that learn meta-strategies for contextual query refinements. Our approach uses machine reading to guide the selection of refinement terms from aggregated search results. Agents are then empowered with simple but effective search operators to exert fine-grained and transparent control over queries and search results. We develop a novel way of generating synthetic search sessions, which leverages the power of transformer-based generative language models through (self-)supervised learning. We also present a reinforcement learning agent with dynamically constrained actions that can learn interactive search strategies completely from scratch. In both cases, we obtain significant improvements over one-shot search with a strong information retrieval baseline. Finally, we provide an in-depth analysis of the learned search policies.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/30/2022

Zero-Shot Retrieval with Search Agents and Hybrid Environments

Learning to search is the task of building artificial agents that learn ...
research
12/10/2020

An Integrated Search Framework for Leveraging the Knowledge-Based Web Ecosystem

The explosion of information constrains the judgement of search terms as...
research
06/25/2021

Interactive query expansion for professional search applications

Knowledge workers (such as healthcare information professionals, patent ...
research
06/08/2021

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

We propose to learn to distinguish reversible from irreversible actions ...
research
10/14/2022

Adaptable Claim Rewriting with Offline Reinforcement Learning for Effective Misinformation Discovery

We propose a novel system to help fact-checkers formulate search queries...
research
10/15/2020

Blending Search and Discovery: Tag-Based Query Refinement with Contextual Reinforcement Learning

We tackle tag-based query refinement as a mobile-friendly alternative to...
research
01/24/2021

Medical Information Retrieval and Interpretation: A Question-Answer based Interaction Model

The Internet has become a very powerful platform where diverse medical i...

Please sign up or login with your details

Forgot password? Click here to reset