Boosting Search Engines with Interactive Agents
Abstract
This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. 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 language models through (self-)supervised learning. We also present a reinforcement learning agent with dynamically constrained actions that learns interactive search strategies from scratch. Our search agents obtain retrieval and answer quality performance comparable to recent neural methods, using only a traditional term-based BM25 ranking function and interpretable discrete reranking and filtering actions.
Cite
@article{arxiv.2109.00527,
title = {Boosting Search Engines with Interactive Agents},
author = {Leonard Adolphs and Benjamin Boerschinger and Christian Buck and Michelle Chen Huebscher and Massimiliano Ciaramita and Lasse Espeholt and Thomas Hofmann and Yannic Kilcher and Sascha Rothe and Pier Giuseppe Sessa and Lierni Sestorain Saralegui},
journal= {arXiv preprint arXiv:2109.00527},
year = {2022}
}
Comments
Published in Transactions on Machine Learning Research (06/2022)