% pubman genre = article
@article{item_3259040,
title = {{Toward a sustainable handling of interlinear-glossed text in language documentation}},
author = {List, Johann-Mattis and Sims, Nathaniel A. and Forkel, Robert},
language = {eng},
doi = {10.1145/3389010},
publisher = {Association for Computing Machinery (ACM)},
address = {New York, NY},
year = {2021},
date = {2021},
abstract = {{While the amount of digitally available data on the worlds{\textquotesingle} languages is steadily increasing, with more and more languages being documented, only a small proportion of the language resources produced are sustainable. Data reuse is often difficult due to idiosyncratic formats and a negligence of standards that could help to increase the comparability of linguistic data. The sustainability problem is nicely reflected in the current practice of handling interlinear-glossed text, one of the crucial resources produced in language documentation. Although large collections of glossed texts have been produced so far, the current practice of data handling makes data reuse difficult. In order to address this problem, we propose a first framework for the computer-assisted, sustainable handling of interlinear-glossed text resources. Building on recent standardization proposals for word lists and structural datasets, combined with state-of-the-art methods for automated sequence comparison in historical linguistics, we show how our workflow can be used to lift a collection of interlinear-glossed Qiang texts (an endangered language spoken in Sichuan, China), and how the lifted data can assist linguists in their research.}},
journal = {{ACM Transactions on Asian and Low-Resource Language Information Processing}},
volume = {20},
number = {2},
pages = {1--15},
}