Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation

TL;DR

This paper introduces a novel neural architecture that leverages neighboring geographic feature pronunciations to improve pronunciation prediction and correction, demonstrating effectiveness in geographic and linguistic tasks.

Contribution

The paper proposes a new model that uses neighboring information for pronunciation prediction, applied to geographic names and linguistic cognates, with open-source code provided.

Findings

Effective in correcting geographic name pronunciation errors

Improves cognate reflex prediction accuracy

Open-source implementation available

Abstract

If one sees the place name Houston Mercer Dog Run in New York, how does one know how to pronounce it? Assuming one knows that Houston in New York is pronounced "how-ston" and not like the Texas city, then one can probably guess that "how-ston" is also used in the name of the dog park. We present a novel architecture that learns to use the pronunciations of neighboring names in order to guess the pronunciation of a given target feature. Applied to Japanese place names, we demonstrate the utility of the model to finding and proposing corrections for errors in Google Maps. To demonstrate the utility of this approach to structurally similar problems, we also report on an application to a totally different task: Cognate reflex prediction in comparative historical linguistics. A version of the code has been open-sourced (https://github.com/google-research/google-research/tree/master/cognate_inpaint_neighbors).