Interesting problems

Semantic Search in Unstructured documents

1. Important KEYWORD EXTRACTOR
   • Extractor-Github-link
   • Extractor-Github-link
   • Unsupervised Approach for Automatic Keyword Extraction using Text Features.
   • YAKE
2. Abbreviations expansion
3. Building dictionary / vocabulary
   • single words
     1. Using our custom built word2vec using GENSIM + Spacy 1. spacy vector similarity
   • learn phrases 1. link-1 1. link-2
4. Policy Number Extraction using BiLSTM-CRF
5. Providing reverse dictionary
   • Github-link
6. Semantic Search
   • using BERT
   • Simaese BERT for Search
   • Semantic Search using FAISS- Facebook Index
   • Semantic Search using embeddings
7. Text generation for suggesting keyword queries
8. Visual search engine
9. NBoost for elasticsearch
   • Link-1
   • Link-2
   • Link-3

Links that were useful while working on Semantic Search

Here are some of the links that might be useful for semantic search engine related work.

1. Fuzzy query on elasticsearch
   • query
2. Synonym query elasticsearch
   • query
3. Semantic search using BERT
   • BERT
   • Siamese-Bert-Networks
4. Semantic Search using embeddings
   • Simple stackoverflow Search Engine
5. Use embeddings with the Elastic index
   • Text Similarity with Vectors in Elastic
6. Use Doc2Vec to find similar documents
   • https://stackoverflow.com/questions/42781292/doc2vec-get-most-similar-documents
   • https://kanoki.org/2019/03/07/sentence-similarity-in-python-using-doc2vec/
7. People I follow for this topic
   • Goku Mohandas
   • Pratik Bhavsar