In our lab meeting tomorrow, Jetic will give a depth presentation on Knowledge-Base Systems.
Here is the title and abstract:
Neural Knowledge-Based Systems in NLP
Abstract: Recent years have seen wide applications of external knowledge sources in end-to-end NLP tasks. Statistical and rule-based methods often rely on utilisation of logical representations, which do allow for easier integration but is limited when it comes to complex implicit inference. For neural models, the ability to better handle ambiguous information has allowed for far more powerful inference and deduction capabilities, but since neural network’s internal states are often represented as uninterpretable vectors, more efforts are necessary to leverage structured knowledge and develop more extensible and powerful intelligent agents. This paper highlights recent advances in utilisation of knowledge bases in neural models, and also important research topics around neural knowledge bases themselves.
Tuesday, Jan 21st, 09:30 a.m. TASC1 9408. Title: Neural Knowledge-Based Systems in NLP