# Neural Extractive Search

arXiv: https://arxiv.org/abs/2106.04612 · HTML: https://mlsanity.com/paper/2106.04612/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [CORD-19: The COVID-19 Open Research Dataset](https://mlsanity.com/paper/2004.10706/) (2020)
- [A Deep Look into Neural Ranking Models for Information Retrieval](https://mlsanity.com/paper/1903.06902/) (2019)
- [Syntactic Search by Example](https://mlsanity.com/paper/2006.03010/) (2020)
- [Interactive Extractive Search over Biomedical Corpora](https://mlsanity.com/paper/2006.04148/) (2020)
- [Extreme Extraction: Only One Hour per Relation](https://mlsanity.com/paper/1506.06418/) (2015)

## Built on by (most cited first, 2 of 2)

- [SynKB: Semantic Search for Synthetic Procedures](https://mlsanity.com/paper/2208.07400/) (2022)
- [Hierarchy Builder: Organizing Textual Spans into a Hierarchy to Facilitate Navigation](https://mlsanity.com/paper/2309.10057/) (2023)

## Abstract (arXiv)

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 urlhttps://spike.neural-sim.apps.allenai.org/ and a video demonstration is available at urlhttps://vimeo.com/559586687.