1) What do you think about hybrid approach: hypergraphs + large-scale NLP models (transformers)?
2) How far we're from real self-evolving cognitive architectures with self-awareness features? Is it a question of years, months, or it's already solved problem?
We're a data science R&D company founded in 2017 with 4 core team members: 2 co-founders, technical (CTO) and non-technical (CEO), a data scientist and software engineer, focused on large-scale NLP projects development with state-of-the-art models. We are located in Kyiv, Ukraine, with sales representatives in Canada (Toronto), United states (New York) and UAE (Dubai).
We also have proprietary product - bio-medical question-answering system, and received grant from the US for the further R&D.
Last year the income of the company reached $150k, and we're planning to make 5x in 2020.
We're looking for:
- Technical or non-technical co-founder (equity sharing) who has connections and will be able to represent us to Fortune 1000 companies.
- Technical or non-technical co-founder (equity sharing) or business-partners who has connections with investors in Palo Alto / San Francisco and will be able to represent us.
- Business partners, who interested to sell our products or services
2) How far we're from real self-evolving cognitive architectures with self-awareness features? Is it a question of years, months, or it's already solved problem?
3) Does it make sense to use embeddings like https://github.com/facebookresearch/PyTorch-BigGraph to achieve better results?
4) Why Cycorp decided to limit communication and collaboration with scientific community / AI-enthusiasts at some point?
5) Did you try to solve GLUE / SUPERGLUE / SQUAD challenges with your system?
6) Is Douglas Lenat still contribute actively to the project?
Thanks