@inproceedings{L16-1310,
 abstract = {Recently, there has been an explosion in the availability of large, good-quality cross-linguistic databases such as WALS (Dryer \& Haspelmath, 2013), Glottolog (Hammarstrom et al., 2015) and Phoible (Moran \& McCloy, 2014). Databases such as Phoible contain the actual segments used by various languages as they are given in the primary language descriptions. However, this segment-level representation cannot be used directly for analyses that require generalizations over classes of segments that share theoretically interesting features. Here we present a method and the associated R (R Core Team, 2014) code that allows the flexible definition of such meaningful classes and that can identify the sets of segments falling into such a class for any language inventory. The method and its results are important for those interested in exploring cross-linguistic patterns of phonetic and phonological diversity and their relationship to extra-linguistic factors and processes such as climate, economics, history or human genetics.
},
 address = {Portorož, Slovenia},
 author = {Dan Dediu and Scott Moisik},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {1955--1962},
 publisher = {European Language Resources Association (ELRA)},
 title = {Defining and Counting Phonological Classes in Cross-linguistic Segment Databases},
 url = {https://www.aclweb.org/anthology/L16-1310},
 year = {2016}
}