On Mono- and Multilingual Word embeddings for NLP
From International Center for Computational Logic
On Mono- and Multilingual Word embeddings for NLP
Thesis defence by Anatoly Zelenin
- Location: APB 3027
- Start: 25. February 2016 at 1:30 pm
- End: 25. February 2016 at 2:30 pm
- Research group: Computational Logic
- Event series: KBS Seminar
- iCal
A fundamental problem of Natural Language Processing is to find a good numerical representation of words to be used in further processing steps. We present different recent mono- and bilingual approaches to map words into vector spaces. Knowing them we focus on issues of existing Multilingual approaches and discuss how to improve them further to build the foundation for systems analyzing Social Media posts from all over the world.