GNES is Generic Neural Elastic Search, a cloud-native semantic search system based on deep neural network.

🔎 Search the information available on a webpage using natural language instead of an exact string match.

Top2Vec learns jointly embedded topic, document and word vectors.

NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)

Code For Medium Article: "How To Create Natural Language Semantic Search for Arbitrary Objects With Deep Learning"

Weaviate is a cloud-native, realtime vector search engine that allows you to bring your machine learning models to scale

it's all about search and its awesomeness

Train a Word2Vec model or LSA model, and Implement Conceptual Search\Semantic Search in Solr\Lucene - Simon Hughes Dice.com, Dice Tech Jobs

a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)

Making BERT stretchy. Semantic Elasticsearch with Sentence Transformers

The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!

Dice.com repo to accompany the dice.com 'Vectors in Search' talk by Simon Hughes, from the Activate 2018 search conference, and the 'Searching with Vectors' talk from Haystack 2019 (US). Builds upon my conceptual search and semantic search work from 2015

Fast Full Text Search based on BM25

Examples of Solr configuration entries for Solr plugins and Conceptual Search\Semantic Search from Simon Hughes Dice.com

Distributed, fault tolerant batch processing for Natural Language Applications and Search, using remote partitioning

Expose a Top2Vec model with a REST API.

An easy to use framework for large-scale fact-checking and question answering

Dice.com's relevancy feedback solr plugin created by Simon Hughes (Dice). Contains request handlers for doing MLT style recommendations, conceptual search, semantic search and personalized search

Semantic Search for Sustainable Development is experimental code for searching documents for text that "semantically" corresponds to any of the UN's Sustainable development goals/targets. For example, it can be used to mine the national development plan documents of a country and identify pieces of text that correspond to any of the SDGs in order to verify alignment of the plan with the SDGs.

Document Search Engine project with TF-IDF abd Google universal sentence encoder model

Semantic Search using FAISS & ElasticSearch

A simple semantic search engine for scientific papers.

Towards an Understanding of Entity-Oriented Search Intents - ECIR'18

Deeplearing based Reverse Image Search using Annoy library

IntentsKB: A Knowledge Base of Entity-Oriented Search Intents - CIKM'18

map of russian nlp papers

The Ontology, Dataset and Knowledge Search Engine