When privacy matters! A series of challenges for chatbots in data-sensitive businesses such as healthcare and finance by Christophe Willemsen
Meetup: Integration of Chatbots in Healthcare and BFSI, Dubai, 1.11.2018
Read the interview with our Chief Data Scientis Alessandro Negro published on Neo4j blog, where he talks about how GraphAware uses natural language processing to help companies gain a better understanding of the knowledge that is spread across their organization.Read the interview
Watch a talk by Eric Wespi from Boston Scientific and GraphAware's Eric Spiegelberg given at GraphConnect NY 2018.
Dr. Alessandro Negro, Chief Scientist at GraphAware, presents on knowledge graphs at GraphTour DC.
View the slides from Dr. Alessandro Negro's presentation at GraphTour DC on how to convert unstructured data silos into powerful knowledge graphs.
In this talk, Luanne talks about ways how to use graphs in order to reduce chaos while delivering complex projects. Streamlining dependencies by promoting zero waste.
The age of touch could soon come to an end. From smartphones and smartwatches to home devices and in-car systems, touch is no longer the primary user interface. In this talk, Christophe will guide you through the design of Voice-Driven UIs and show why Neo4j, the world's leading graph database, is a suitable engine for storing and computing context-aware intents in order to improve the user experience.
If your data ingestion requirements have grown beyond importing occasional CSV files then this talk is for you. Neo4j-Databridge from GraphAware is a comprehensive ETL tool specifically built for Neo4j. It has been designed for usability, expressive power and high performance to address the most common isues faced when importing data into Neo4j - multiple data sources and type, very large data sets, bespoke data conversions, non-tabular formats, filtering, merging and de-duplication, as well as bulk imports and incremental updates. Presentation by Vince Bickers.
View Christophe's slides from the GraphTour Meetup that took place March 1, 2018.
Knowledge Graphs are becoming the de-facto solution for managing complex aggregated knowledge, and Neo4j is the leading platform for storing and querying connected data. In this talk, Christophe will describe a graph-centric cognitive computing pipeline and detail the process from the ingestion of unstructured text up to the generation of a knowledge graph, queryable using natural language through chatbots built with IBM Watson Conversation.
Graph-Powered machine learning is becoming an important trend in Artificial Intelligence, transcending a lot of other techniques. Using graphs as basic representation of data for ML purposes has several advantages: (i) the data is already modeled for further analysis, explicitly representing connections and relationships between things and concepts; (ii) graphs can easily combine multiple sources into a single graph representation and learn over them, creating Knowledge Graphs; (iii) improving computation performances and quality. The talk will discuss these advantages and present applications in the context of recommendation engines and natural language processing.
Graph-based machine learning is becoming an important trend in Artificial Intelligence, transcending a lot of other techniques. Using graphs as basic representation of data for ML purposes has several advantages: (i) the data is already modeled for further analysis, explicitly representing connections and relationships between things and concepts; (ii) graphs can easily combine multiple sources into a single graph representation and learn over them, creating Knowledge Graphs; (iii) improving computation performances and quality. The talk will discuss these advantages and present applications in the context of recommendation engines and natural language processing.
Vlasta Kus talked about the advantages of graph-based natural language processing (NLP) using a public NASA dataset as example. From his abstract: "[...] we are building a platform (from large part open-source) that integrates Neo4j and NLP (such as Named Entity Recognition, sentiment analysis, word embeddings, LDA topic extraction), and we test and develop further related features and tools, lately, for example, integrating Neo4j and Tensorflow for employing deep learning techniques (such as deep auto-encoders for automatic text summarisation)."
View Vlasta's slides from Paris Meetup in March 5, 2018.
The GraphAware Audit module seamlessly and transparently captures a full audit history who, when, and how a graph was modified.
View Luanne's slides from GraphConnect Europe 2017.
In this talk, Christophe will describe a graph-centric cognitive computing pipeline and detail the process from the ingestion of unstructured text up to the generation of a knowledge graph, queryable using natural language through chatbots built with IBM Watson Conversation.
GraphAware is pleased to announce the release of “Neo4j : Déploiement”, a french book explaining how to use Neo4j in a real life project. The book is co-authored by Sylvain Roussy and Nicolas Rouyer along with our Senior Consultant Nicolas Mervaillie. You can get it from your favorite (french) bookstore or on D-Booker website.Buy the book
See how combining technologies adds another level of quality to search results. In this new Refcard, we include code and examples for using Elasticsearch to enable full-text search and Neo4j to power graph-aided search.Download PDF
A few weeks ago Spring Data Neo4j version 5 was released as part of the Spring Data 2.0 release train. Time to present the Spring way to work with Neo4j and introduce the latest features SDN 5 and its supporting library Neo4j-OGM 3 provide. The talk will also give an overview of the overall architecture and shows examples how to build modern, compact back-ends and web-applications using Spring Data Neo4j. Of course we will give a glance of what the future will bring to Spring Data Neo4j.
In 2016, 25% of web searches on Android were made by voice and this percentage is predicted to double by 2018. From Amazon Alexa to Google Home, smartwatches and in-car systems, touch is no longer the primary user interface. In this talk, Alessandro and Christophe will demonstrate how graphs and machine learning are used to create an extracted and enriched graph representation of knowledge from text corpus and other data sources. This representation will then be used to map user intents made by voice to an entry point in this Neo4j backed knowledge graph. Every user interaction will then have to be taken into account at any further steps and we will highlight why graphs are an ideal data structure for keeping an accurate representation of a user context in order to avoid what is called machine or bot amnesia. The speakers will then conclude the session by explaining about how recommendations algorithms are used to predict next steps of the user's journey.
Neo4j as a viable tool in a relevant search ecosystem demonstrating that it offers not only a suitable model for representing several complex data, like text, user models, business goal, and context information but also providing efficient ways for navigating this data in real time. Moreover at an early stage in the "search improvement process" Neo4j can help relevance engineers to identify salient features describing the content, the user or the search query, later will be helpful to find a way to instruct the search engine about those features through extraction and enrichment.
Moreover, the talk demonstrates how the graph model can provide the right support for all the components of the relevant search and concludes with the presentation of a complete end-to-end infrastructure for providing relevant search in a real use case. It will show how it is integrated with other tools like Elasticsearch, Apache Kafka, Stanford NLP, OpenNLP, Apache Spark.
SDN is a Spring Data project for Neo4j. It uses Neo4j-OGM under the hood (very much like Spring Data JPA uses JPA) and provides functionality known from the Spring Data world like repositories, derived finders or auditing. Neo4j recently released Spring Data 2.0 (Kay) / Spring Data Neo4j 5.0 and in this session we'll show some of the new cool features. This release contains support for dynamic properties, schema based loading, field access only, and more.
In this talk, Luanne will share insights about the business value of knowledge graphs and their contribution to relevant search in an e-commerce domain for a Neo4j customer. With text search and catalog navigation being the entry point of users to the system and in fact, driving revenue, the talk will explain the challenges of relevant search and how graph models address them. Dr. Alessandro will then talk about various techniques used for information extraction and graph modelling. He will also demonstrate how to seamlessly introduce knowledge graphs into an existing infrastructure and integrate with other tools such as ElasticSearch, Kafka, Apache Spark, OpenNLP and Stanford NLP.
Here's another great interview with a long time Graphista that has done a lot of really interesting work in our French community, and is now having lots of graph-fun at GraphAware: Nicolas Mervaillie.
Speaker: Dr. Alessandro Negro, Chief Scientist at GraphAware. September 20th 2017 at Westin Hotel, Abu Dhabi UAE.
Speaker: Vince Bickers, Principal Consultant at GraphAware. September 20th 2017 at Westin Hotel, Abu Dhabi UAE.
Streamed live on Aug 3, 2017 Following on from the Introduction to Neo4j Bolt Drivers in this session we'll be hosting a roundtable where Neo4j driver authors will be sharing their experiences.
Vince Bickers, Principal Consultant, GraphAware:Neo4j-Databridge is a fully-featured ETL tool specifically built for Neo4j, and designed for usability, expressive power and high performance. It has been created to help solve the most common problems faced by large enterprises when importing data into Neo4j - data locality, multiple data sources and formats, performance when loading very large data sets, bespoke data conversions, inclusion of non-tabular data, filtering, merging and de-duplication...
In this webinar, we’ll take a quick tour of the main features of Neo4j-Databridge and understand how it can to help to solve these problems and facilitate importing your data easily and quickly into Neo4j.
During this talk, Christophe, Principal Consultant at GraphAware will walk you through the design of building Conversational Bots. To this end, he used Amazon Alexa and combined it with a Natural Language Processing stack backed by a Neo4j Graph Database.
You will discover the basics of an Amazon Alexa skill and how the user experience with voice devices can be enhanced with graph based algorithms such as recommendations.
At GraphDB Meetup Czech Republic in Prague, Christophe Willemsen talks about creating a chatbot with Amazon Alexa, Neo4j and GraphAware NLP
Michael Hunger introduces Neo4j to the audience of the Czech GraphDB Meetup in Prague, Czech Republic
In the previous years we have got the Polyglot Persistence. This is a fancy term which means that when storing data, it is best to use multiple data storage technologies, chosen based upon the way data is being used by. If we have multiple persistence, then sometimes we need polyglot operations. One of the most popular use case in Big Data is searching. Almost all websites provide a search function to their users, to be able to find what they are looking for. Usually it is an Apache Lucene based solution, like Elasticsearch or Solr. I will show you how to enrich this kind of searching with the power of graph based searches, and implement a polyglot search functionality, where the results are based on the cooperation of a search engine and a graph based real time recommendation.
With more than 9 million users and 21 million repositories, Github is the world's biggest code sharing platform. Its API offers a window to the public activity of about 600.000 events a day. In this talk you will discover how this amount of user activities transformed in a suitable graph can become a new source of knowledge.
A great part of the world's knowledge is stored using text in natural language, but using it in an effective way is still a major challenge. Natural Language Processing (NLP) techniques provide the basis for harnessing this huge amount of data and converting it into a useful source of knowledge for further processing. It uses computer science, artificial intelligence and formal linguistics concepts to analyze natural language, aiming at deriving meaningful and useful information from text.
Ever struggle with writes performance in Cypher? This Lightning talk is for you! In only 15 minutes, Christophe will show you some tips and tricks for making your Cypher write transactions as fast as possible.
Presentation at Big Data Universe 2.0 in Budapest
Building Spring Data Neo4j 4.1 Applications Like A Superhero: The latest release of Spring Data Neo4j 4.1 offers advanced features to map your Java domain models to the Neo4j Graph Database. Powered by the Neo4j-OGM library, it offers you the convenience and familiarity of Spring-based programming. After this introductory tour of its features, followed by a demonstration of how easy it is to rapidly build an application, you'll have the confidence to start developing with Spring Data Neo4j 4.1 today.
Graph Databases are naturally well-suited for building recommendation engines. In this talk, Christophe will share his experience building a number of production-ready recommendation engines using Neo4j and introduce the open-source GraphAware Reco4PHP Library, which enables PHP developers to rapidly build their own recommendation systems.
A great part of the world’s knowledge is stored using text in natural language, but using it in an effective way is still a major challenge. Natural Language Processing (NLP) techniques provide the basis for harnessing this huge amount of data and converting it into a useful source of knowledge for further processing. By Alessandro Negro, Chief Scientist, GraphAware.
@Leisure Group case study
‘GraphAware successfully implemented a real-time recommendation engine on our site in just two weeks. That is an astonishingly short time to production.’
--David Stephenson, Managing Director, DSI Analytics and interim Head of Analytics, BelvillaRead the Case Study
The Dataportal is a data resource search engine which connects users with visualizations, tools, curated data, and metrics to do their job more effectively. It aids with data discovery, trust, and empowers Airbnb employees to be ""data informed"" in their decision making, and encourages a culture of self-service.
Podcast Interview with Michal Bachman, GraphAware by Rik Van Bruggen.
Bryce Merkl Sasaki from Neo4j chatted with Christophe Willemsen, our Senior Neo4j Consultant Christophe and Bryce spoke at GraphConnect San Francisco last October.
See the slides form the keynote given by Chris Williams and John Bodley from AirBnB.
Michael Bachman of GraphAware discusses how to build a high-performance recommendation engine with Neo4j. He discusses business and technical challenges and shows their Java and Cypher code.
InfoJobs case study
‘GraphAware didn’t just help us build our recommendation service: they helped our developers acquire a whole new set of programming skills.’
--Marc Pou, Product Owner, InfoJobsRead the Case Study
Vince Bickers, Principal Consultant at GraphAware and main contributor to Spring Data Neo4j, gives an update on the release of the new version of SDN.
From user preferences and location to time of day and weather, complex context representations have been the key to delivering personalised content. Graph databases excel at dealing with large amounts of complex data and therefore, they have been at the core of many modern real-time recommendation systems. In the near future, graph databases will play an equally important role in search personalisation.
In this talk, Michal will introduce real-world content personalization requirements and show how Neo4j has been used to implement them. He will show how much recommendation and search engines have in common and give an overview of the latest innovations in the field of search personalisation.
Vince Bickers, Principal Consultant, GraphAware, contributor to Spring Data Neo4j:Learn about the latest version (v4) of Spring Data Neo4j (SDN). Neo4j is the world’s leading graph database, a scalable, open-source NoSQL solution for your data relationships. Spring Data offers convenient APIs for Spring Developers to build modern applications using new data stores. It supports object-mapping, DAO repositories and consistent access to underlying database APIs.
Bryce Merkl Sasaki of Neo4j interviews Luanne Misquitta, Senior Consultant at GraphAware, during Graph Connect Europe 2016. Luanne Misquitta talks about Spring Data Neo4j 4.x, a completely rewritten version of SDN to support a high performance object/graph map. Version 4.1 supports both an embedded library as well as Bolt, the new binary protocol for Neo4j.
Graphgen aims at helping people prototyping a graph database, by providing a visual tool that ease the generation of nodes and relationships with a Cypher DSL. Many people struggle with not only creating a good graph model of their domain but also with creating sensible example data to test hypotheses or use-cases. Graphgen aims at helping people with no time but a good enough understanding of their domain model, by providing a visual dsl for data model generation which borrows heavily on Neo4j Cypher graph query language. The ascii art allows even non-technical users to write and read model descriptions/configurations as concise as plain english but formal enough to be parseable. The underlying generator combines the DSL inputs (structure, cardinalities and amount-ranges) and combines them with a comprehensive fake data generation library to create real-world-like datasets of medium/arbitrary size and complexity. Users can create their own models combining the basic building blocks of the dsl and share their data-descriptions with others with a simple link.
GraphAware: Towards Online Analytical Processing in Graph Databases
MSc. Thesis submitted for MSc. program in Computing at Imperial College London, written by GraphAware's managing director Michal Bachman.Download PDF
Real-Time Recommendations with Graphs and the Future of Search: Michal Bachman, Managing Director, GraphAware. Michal talks about how they use Neo4j in combination with Elasticsearch to power real-time recommendations.
Applying the GraphAware Framework. #GraphConnect, #Neo4j, #Michal Bachman, #GraphAware, #GraphAware Framework