Neural Extractive Search
This addresses the need for domain experts to efficiently extract structured data from large text collections, presenting an incremental improvement over syntactic-based methods.
The paper tackles the problem of extracting structured information from large corpora by proposing a new search paradigm called 'extractive search', which uses capture-slots in queries to improve recall through neural retrieval and alignment, demonstrating a prototype system with available resources.
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}.