Past, Present, Future: A Computational Investigation of the Typology of Tense in 1000 Languages
This work addresses the challenge of linguistic typology for low-resource languages, offering a scalable approach that is incremental over existing methods.
The authors tackled the problem of crosslingual analysis for low-resource languages by developing SuperPivot, a method that leverages a superparallel corpus with over 1000 languages, and demonstrated its effectiveness for tense typology, producing the largest computational study of its kind.
We present SuperPivot, an analysis method for low-resource languages that occur in a superparallel corpus, i.e., in a corpus that contains an order of magnitude more languages than parallel corpora currently in use. We show that SuperPivot performs well for the crosslingual analysis of the linguistic phenomenon of tense. We produce analysis results for more than 1000 languages, conducting - to the best of our knowledge - the largest crosslingual computational study performed to date. We extend existing methodology for leveraging parallel corpora for typological analysis by overcoming a limiting assumption of earlier work: We only require that a linguistic feature is overtly marked in a few of thousands of languages as opposed to requiring that it be marked in all languages under investigation.