Towards Universal Syntactic Processing of Natural Language (invited talk)
Slav Petrov · 2014
In this talk I will first describe some techniques for projecting syntactic information across language boundaries, allowing us to build models for languages with no labeled training data. I will then present some ongoing work towards a universal representation of morphology and syntax that makes it possible to model language phenomena across language boundaries in a consistent way. Finally, I will highlight some examples of how we have successfully used syntax at Google to improve downstream applications like question answering and machine translation. 2 Author’s Biography