Neural Extractive Search

TL;DR

This paper introduces the extractive search paradigm, combining syntactic structures with neural retrieval to enable domain experts to efficiently extract structured information from large text corpora.

Contribution

It proposes the extractive search paradigm and demonstrates a neural retrieval system that improves recall in structured information extraction tasks.

Findings

Neural retrieval enhances recall in extractive search.

Prototype system shows practical benefits for domain experts.

Available online for demonstration and testing.

Abstract

Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called ``extractive search'', in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and its benefits and potential. Our prototype is available at \url{https://spike.neural-sim.apps.allenai.org/} and a video demonstration is available at \url{https://vimeo.com/559586687}.