Awesome Semantic-Search

Logo made by @createdbytango.

Following repository aims to serve a meta-repository for Semantic Search and Semantic Similarity related tasks.

Semantic Search isn't limited to text! It can be done with images, speech, etc. So there are numerous different use-cases and applications of semantic search.

Contributions / Milestones

Have a look at the project board for the task list

Table Of Contents

• Papers
  • 2014
  • 2015
  • 2016
  • 2017
  • 2018
  • 2019
  • 2020
  • 2021
  • ?2021/2020?
• Libraries and Tools
• Datasets

Papers

2014

• A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval 📄

2015

• Skip-Thought Vectors 📄

2016

• Bag of Tricks for Efficient Text Classification 📄
• Enriching Word Vectors with Subword Information 📄
• Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs
• On Approximately Searching for Similar Word Embeddings 📄

2017

• Supervised Learning of Universal Sentence Representations from Natural Language Inference Data 📄

2018

• Universal Sentence Encoder 📄
• Learning Semantic Textual Similarity from Conversations 📄
• Google AI Blog: Advances in Semantic Textual Similarity 📄
• Optimization of Indexing Based on k-Nearest Neighbor Graph for Proximity Search in High-dimensional Data

2019

• LASER: Language Agnostic Sentence Representations 📄
• Document Expansion by Query Prediction 📄
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks 📄
• Multi-Stage Document Ranking with BERT 📄

2020

• Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned 📄
• PASSAGE RE-RANKING WITH BERT 📄
• CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization 📄
• LaBSE:Language-agnostic BERT Sentence Embedding 📄
• Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset 📄
• DeText: A deep NLP framework for intelligent text understanding 📄
• Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation 📄
• Pretrained Transformers for Text Ranking: BERT and Beyond 📄

2021

• Augmented SBERT 📄
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models 📄
• Compatibility-aware Heterogeneous Visual Search 📷

?2021/2022?

• Learning Personal Style from Few Examples

Libraries and Tools

• fastText
• Universal Sentence Encoder
• SBERT
• LaBSE
• LASER
• Haystack
• Jina.AI
• SentEval Toolkit
• BEIR :Benchmarking IR
• Which Frame?
• PySerini
• milvus
• weaviate
• natural-language-youtube-search
• same.energy
• scaNN
• annoy
• faiss
• DPR
• rank_BM25
• nearPy
• vearch
• PyNNDescent
• pgANN

Datasets

• Semantic Text Similarity Dataset Hub