Skip to content
Graphs ❤ NLP

Details

Guys, I would like to use this meetup group to promote our next event. It has NLP, Graphs, and some Machine Learning too. So if you are interested then fell free to join us.
This event is announced in the Neo4j Budapest Meetup (https://www.meetup.com/neo4j-budapest-users/) Group, and in the Hungarian Natural Language Processing Meetup (https://www.meetup.com/Hungarian-nlp/) Group too.

Meetup Agenda

18:00-18:30 Registration
18:30-19:15 Gábor Berend: Discretized Word Representations Meet Knowledge Graphs
19:15-19:45 Break
19:45-20:30 Dr. Alessandro Negro: Relevant Search Leveraging Knowledge Graphs with Neo4j

Details:

Gábor Berend: Discretized Word Representations Meet Knowledge Graphs
Continuous word representations enjoy great prevalence in most natural language processing applications nowadays. Despite their effectiveness and widespread popularity, these representations also have some less appealing behavior. In the talk, I will argue that by performing discretization of continuous word representations, it not only becomes possible to obtain more accurate performance for various natural language processing tasks, but at the same time it can alleviate some undesired characteristics of standard word embeddings. It will be demonstrated that discretized word representations convey human interpretable commonsense knowledge similar to those being present in the ConcepNet knowledge graph.

About the speaker - Gábor Berend
Gábor Berend is an assistant professor at the Institute of Informatics, University of Szeged. Within natural language processing his main research interest is focused on semantic aspects of computational linguistics. Besides natural language processing, he also has a keen interest in network science and coming up with algorithms that lie in the intersection of the two subfields.

Dr. Alessandro Negro: Relevant Search Leveraging Knowledge Graphs with Neo4j
"Relevance is the practice of improving search results for users by satisfying their information needs in the context of a particular user experience, while balancing how ranking impacts our business's needs." [D. Turnbull, J. Berryman - Relevant Search, Manning]Providing relevant information to the user performing search queries or navigating the site is always a complex task that cannot be solved just using some search software. It requires a process of progressive improvements and self tuning parameters together with the infrastructure that can support it. Moreover such search infrastructure must be inserted seamlessly and smoothly into the existing platform, accessing to the relevant data flow and providing always updated data.
The speaker will highlight 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 will demonstrate 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.

About the Speaker - Dr. Alessandro Negro
Alessandro has been a long-time member of the graph community and he is the main author of the first-ever recommendation engine based on Neo4j. At GraphAware, he specialises in recommendation engines, graph-aided search, and NLP. He has recently built an application using Neo4j and Elasticsearch aimed at personalising search results, utilizing several machine learning algorithms, natural language processing and ontology hierarchy. Before joining the team, Alessandro has gained over 10 years of experience in software development and spoke at many prominent conferences, such as JavaOne. Alessandro holds a Ph.D. in Computer Science from University of Salento.

For any futher requests or support contact the event organiser Janos Szendi-Varga on tel. +36306311873.

Where is Impact HUB?

https://secure.meetupstatic.com/photos/event/a/8/f/1/600_465283249.jpeg

Photo of Budapest Machine Learning Meetup group
Budapest Machine Learning Meetup
See more events
Impact Hub Budapest
Ferenciek tere 2. Budapest 1053 1st floor on the left · Budapest