Registrations have closed.

Extracting Entities and Relations in Financial Data

by
180 180 people viewed this event.

About this event

Massive volumes of finance-related data are created on the Internet daily, whether on question-answering forums, news articles, or stock analysis sites. This data can be critical in the decision-making process for targeting investments in the stock market.

The aim of this session is to extract information from such sources in order to utilize the volumes of data which is impossible to process manually. The study presented in this session is based on the employment of different models for word embedding and different Deep Learning classification architectures for extracting the entities and predicting relations between them.

Furthermore, the multilingual abilities of a joint pipeline are being explored by combining English and German corpora. For both subtasks, we will show state-of-the-art performances of 97.69% F1 score for named entity recognition and 89.70% F1 score for relation extraction.

Join us on 29.11.2022, from 4:30 PM CET, as we’ll have Igor Mishkovski, Ph.D., dive deep into the subject!

Agenda:

  • Introduction;
  • Dataset description;
  • Methodologies;
  • Results and Discussion;
  • Future Work and Conclusion.

 

About the Speaker

Born in 1981 in Skopje, Igor Mishkovski started his journey as a tech professional when he graduated in Electrical Engineering in Skopje in 2005, going on to acquire a master’s degree, and eventually a doctorate in the area of vulnerability and dynamical processes of complex networks at Politecnico di Torino in 2012.

Immediately after earning his bachelor’s degree, he started working as an assistant at Institute of Computer Technology in Electrical and Computer Engineering in Skopje. From 2007 he started working as teaching assistant for the subjects in the field of computer technology and informatics. During his work he has provided a significant contribution to the design, creation and organization of the exercises and the teaching material.

He has been involved in the research in the field of complex computer networks and has published more than 70 scientific papers in international and domestic conferences and journals. Participated in the preparation of 5 books, as well as a number of scientific research and application projects. Areas of his research interests are data science, NLP, machine learning, fintech, complex networks, application software and web technology.

The Re:Imagine Sessions are designed with one goal in mind – to give experts, leaders, and people with ideas the platform to share their know-how, experience, and findings – and maybe even find like-minded people to join them on their journey! The sessions are powered by IT Labs – a company with a vision to enable clients to compete through tech while providing a platform for bright heads to grow and develop into top-notch tech professionals.

We invite you for a networking drink afterward.

If you are not based in Skopje, no worries. You can attend this event ONLINE by saving your seat today on this link.

 

Date And Time

2022-11-29 @ 04:30 PM (CET)
 

Event Types

 

Event Category

Share With Friends