Hello. I am a final year PhD student at the Computer Lab, in the Natural Language and Information Processing group. My supervisor is Stephen Clark. I am currently thinking about distributional models of inference computational creativity and narrative problems in text generation deep generative models with sequential likelihoods. Here is my CPGS report with my (out of date) PhD proposal. During an internship at Deepmind, I also thought a little bit about emergent communication in non-cooperative environments

I also no longer organise the Cambridge NLIP group seminars. If you'd like to give a talk at our seminar, you can still drop me an email at kc391 AT cam DOT ac DOT uk.

Before that, I did 4 years of maths at Cambridge, including Part III, where I took mainly logic courses. Here is my Part III essay, about models of set theory where every set of reals is Lebesgue measurable. After that, I worked for a year as a software developer, and then started my PhD.


Generating syntactically varied realisations from AMR graphs
Kris Cao and Stephen Clark

Whole-sentence Topic Models
Kris Cao and Stephen Clark

Emergent communication through negotiation
Kris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z Leibo, Karl Tuyls and Stephen Clark
In Proceedings of International Conference on Learning Representations (ICLR-2018)

Latent variable dialogue models and their diversity
Kris Cao and Stephen Clark
In Proceedings of European Chapter of the Association of Computational Linguistics (EACL-2017)

A Joint Model of Word Embedding and Word Morphology
Kris Cao and Marek Rei
In Proceedings of 1st Workshop on Representation Learning for NLP (RepL4NLP-2016)


I have supervised Part II Quantum Computing and Natural Language Processing for CS undergraduates, and Part II Logic and Set Theory for maths undergraduates.


I was part of the organising committee of the Workshop on Learning to Generate Natural Language and the 3rd Workshop on Representation Learning for Language. I have also reviewed for various workshops and conferences.