Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines
| Autoři | |
|---|---|
| Rok publikování | 2017 |
| Druh | Článek ve sborníku |
| Konference | Proceedings of the 2nd Workshop on Representation Learning for NLP, RepL4NLP 2017 c/o ACL 2017 |
| Fakulta / Pracoviště MU | |
| Citace | |
| www | |
| Doi | http://dx.doi.org/10.18653/v1/W17-2611 |
| Obor | Informatika |
| Klíčová slova | full-text search; similarity search; vector space; embeddings |
| Popis | Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to ‘vector similarity searching’ over dense semantic representations of words and documents that can be deployed on top of traditional inverted-index-based fulltext engines, taking advantage of their robustness, stability, scalability and ubiquity. We show that this approach allows the indexing and querying of dense vectors in text domains. This opens up exciting avenues for major efficiency gains, along with simpler deployment, scaling and monitoring. The end result is a fast and scalable vector database with a tunable trade-off between vector search performance and quality, backed by a standard fulltext engine such as Elasticsearch. We empirically demonstrate its querying performance and quality by applying this solution to the task of semantic searching over a dense vector representation of the entire English Wikipedia. |
| Související projekty: |