Evolutionary Neural Architecture Search
We propose an application of evolutionary algorithm to Neural Architecture Search for image and text classification tasks on PyTorch. One of the main issues of evolutionary search is high resource consumption, so one of our main priority is optimisation of the model evaluation.
Knowledge Graph-Based Dialogue Generation
Responses can be more meaningful compared to chit-chat generated responses thanks to usage of facts coming from a knowledge base like Wikidata. The system consists of three components:
- extraction of triplets from Wikidata for entities from the user's utterance;
- triplets ranking (choosing the triplet which is the most appropriate to use for generation of the response utterance);
- generation of the response utterance.
Transformer With Inner Classification Of Memory Tokens In Decoder
During decoding in Transformer, we simultaneously predict the next token and its type: memory or sequence. Memory tokens provide space to store global representations of the input context.