Talks and presentations

DSAA Poster: Fake News Detection Using Multilingual Evidence Permalink

October 06, 2020

Talk, The 7th IEEE International Conference on Data Science and Advanced Analytics, Sydney, Australia

Nowadays, misleading information spreads over the internet at an incredible speed, which can lead to irreparable consequences. As a result, it is becoming more and more essential to combat fake news, especially in the early stages of its origins. Over the past years, a lot of work has been done in this direction. However, all existed solutions have their limitations. One of the main limitations of the current approaches is that the majority of the models are focused only on one language and do not use any multilingual information. In this work, we investigate the new approach of fake news detection based on multilingual evidence. We show effectiveness of the proposed approach in a manual and an automated evaluation experiments.

ViTalk: Virtual Analyst or Human Business Intelligence Permalink

May 10, 2019

Talk, DataFest 2019, Moscow, Russian Federation

NLP solutions in production can be not so easy. We are presenting our NLP-application for BI — virtual analyst ViTalk and our path of development of this solution. ViTalk can deal with natural language request to the KPI of your business (“what is our income”, “show me only last year”, “compare with current”, etc.) While the NLP parts inside are pretty usual, the real-life implementation has faced its own obstacles. We want to share our experience and show that even low-resource unusual data can lead to successful product.