Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation

Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation Llion Jones† Richard Sproat† Haruko Ishikawa† Alexander Gutkin‡ †Google Japan ‡Google UK {llion,rws,ishikawa,agutkin}@google.com Abstract If one sees the place name Houston Mer- cer Dog Run in New York, how does one know how to pronounce it? Assuming one knows that Houston in New York is pro- nounced and not like the Texas city ( ), then one can probably guess that is also used in the name of the dog park. We present a novel architecture that learns to use the pronunciations of neighbor- ing 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 correc- tions 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 his- torical linguistics. A version of the code has been open-sourced.1 1 Introduction In many parts of the world, pronunciation of toponyms and establishments can require local knowledge. Many visitors to New York, for ex- ample, get tripped up by Houston Street, which they assume is pronounced the same as the city in Texas. If they do not know how to pronounce Houston Street, they would likely also not know how to pronounce the nearby Houston Mercer Dog Run. But if some one knows one, that can (usually) be used as a clue to how to pronounce the other. Before we proceed further, a bit of terminol- ogy. Technically, the term toponym refers to the name of a geographical or administrative feature, such as a river, lake, town, or state. In most of what follows, we will use the term feature to refer to these and other entities such as roads, build- ings, schools, and so forth. In practice we will 1https://github.com/google-research/google -research/tree/master/cognate inpaint neighbors. not make a major distinction between the two, but since there is a sense in which toponyms are more basic, and the names of the more general features are often derived from a toponym (as in the Houston Mercer Dog Run example above), we will retain the distinction where it is needed. While features cause not infrequent problems in the US, they become a truly serious issue in Japan. Japan is notorious for having toponyms whose pronunciation is so unexpected that even native speakers may not know how to pronounce a given case. Most toponyms in Japanese are writ- ten in kanji (Chinese characters) with a possible intermixing of one of the two syllabaries, hira- gana or katakana. Thus Ueno is entirely in kanji; Tora no mon has two kanji and one katakana symbol (the second); and Fukiwari Waterfalls has three kanji and one hira- gana symbol (the third). Features more generally tend to have more characters in one of the syl- labaries—especially katakana if, for example, the feature is a building that includes the name of a company as …

Content truncated to 500 words