I built STARLITE, a novel web-based agent platform that allows open,
dynamic execution of agent simulations. Using STARLITE, researchers
can start simulations as web applications and deploy their agents on them dynamically to test
their behaviour and performance. Published in AAMAS15.
More recently, I developed two novel methodologies for the automatic generation of rhythmic poetry in a variety of forms. The first approach used a neural language model trained on a phonetic encoding to learn an implicit representation of both the form and content of English poetry.The second approach considers poetry generation as a constraint satisfaction problem where a generative neural language model is tasked with learning a representation of content, and a discriminative weighted finite state machine constrains it on the basis of form. In a blind indistinguishability test, humans could only differentiate between human and generated poetry 52% of the time. This work is published in ACL17.