SUMMA Open Source Components
Most SUMMA components will be available as Open Source at the end of the project (January 2019). The preliminary (but not confirmed list) of these is as follows:
- Speech to Text technologies:
- Speech Recognition English models
- Speech Recognition Latvian Models
- Punctuation prediction
- Translation technologies:
- Neural Translation Core
- German - English tranlation model
- Latvian - English tranlation model
- Spanish - English tranlation model
- Russian - English tranlation model
- Text enrichment technologies:
- (Multilingual) Topic Labelling
- Storyline Clustering
- Named Entity Recognition
- Knowledge Base Constructor
- Sentence-level Fact Checker