Estimate the degree of similarity between two texts

Compare the most popular ways of computing sentence similarity and investigate how they perform.

FROM Static Word Embedding TO Dynamic (Contextualized) Word Embedding

Language modeling is the task of assigning a probability distribution over sequences of words that matches the distribution of a language.

Disrupting Customer-Centric Journey via a data-driven strategy

Improving the customer journey and providing a positive customer experience (CX) was ranked as the number one trend, as well as top strategic priority, in the survey of global banking leaders for the 2017 Retail Banking Trends and Predictions report.

Network Graph of Word Embeddings [Part 1]

How network embedding graphs can help to solve major open problems in natural language understanding - introduction

Network Graph of Word Embeddings - Node2Vec and implementation on Neo4j via Cypher [Part 2]

Node2Vec creates vector representation for nodes in a network when Word2Vec and Doc2Vec creates vector representations for words in a corpus of text. How to implement two different Neo4j graph databases

Neo4j Graph Database and Python

Load csv file into Neo4j and request it

Distributed Computing & (Py)Spark

MapReduce / Hadoop / tf-idf and PageRank / Spark / Distributed Datasets / SparkSQL / AWS / Data Storage on S3 / Manage a cluster on cloud computing / Cloud Computing / PySpark

A Full free text Search Engine built from ElasticSearch and Flask

Implementing a search feature so that users can find interesting posts using natural language / NLP / [Bonus] : Kibana - load data (e.g csv, txt, ...) via Python, R or Logstash - Queries data straightforward via R or Python [Coming soon]

Access real-time data via Kafka and Storm

Case study based on JC-Decaux API to manage Bicycles pool in near real time [Coming soon]