Towards More Natural Artificial Languages by Prof. Mark Hopkins, Statistics Colloquium

Towards More Natural Artificial Languages by Prof. Mark Hopkins, Computer Science, Williams College, Statistics Colloquium, Wednesday, September 28, 1:10 – 1:50 pm, North Science Building 114, Wachenheim.

Abstract:  A number of papers have recently argued in favor of using artificially generated languages to investigate the inductive biases of linguistic models, or to develop models for low-resource languages with underrepresented typologies. But the promise of artificial languages comes with a caveat: if these artificial languages are not sufficiently reflective of natural language, then using them as a proxy may lead to inaccurate conclusions.  In this paper, we take a step towards increasing the realism of artificial language by introducing a variant of indexed grammars that draw their weights from hierarchical Pitman-Yor processes.  We show that this framework generates languages that emulate the statistics of natural language corpora better than the current approach of directly formulating weighted context-free grammars.