Cover not available
Part of
Variation Rolls the Dice: A worldwide collage in honour of Salikoko S. Mufwene
Edited by Enoch O. Aboh and Cécile B. Vigouroux
[Contact Language Library 59] 2021
► pp. 269–288

Detecting loan words computationally

 | Open University, Netherlands
 | National Museum of Natural History, Paris
 | L-Università ta’ Malta
 | University of Groningen & University of Freiburg
A loanword is a word that is borrowed from one language and adopted into another; examples are the English words toboggan, skunk, and hickory, all of which were borrowed from Algonquian languages. Among languages that are not (closely) related, loan words are recognizable because they are semantically related and are more similar in pronunciation than one would expect by coincidence. This chapter applies techniques for measuring pronunciation similarity, focusing on edit-distance measures and a sound-class based method. The novel issue in loan-word detection is the circumstance that loan words are normally modified to fit the phonology of the borrowing language, meaning that sensitivity in measuring pronunciation similarity may be deprecated.
Keywords: loan words, automatic detection, edit distance, sound class alignment, language contact
Article outline
  • 1.Introduction
  • 2.Mufwene’s perspective
  • 3.Previous work
  • 4.Data
    • Example data
  • 5.Measuring pronunciation similarity
  • 6.General setup
  • 7.Evaluation and results
    • Examples of detected loans
  • 8.Discussion and prospects
    • Conclusions and a speculation
    • Future work
    • Prospects
  • Supplementary data
  • Acknowledgements
  • Notes
  • References
Published online: 12 October 2021
DOI logo
https://doi.org/10.1075/coll.59.11zha
References (31)
References
Black, E., Lafferty, J. & Roukos, S. 1992. Development and evaluation of a broad-coverage probabilistic grammar of English-language computer manuals. In Proceedings of the 30th Annual Meeting of the Association for Computational Linguistics, 185–192. Shroudsburg PA: Association for Computational Linguistics. <[URL]> (permanent archive). DOI logoGoogle Scholar
Collins, M. & Mufwene, S. S. 2005. What we mean when we say “Creole”: An interview with Salikoko S. Mufwene. Callaloo 28: 425–462. DOI logoGoogle Scholar
Dellert, J. 2017. Information-Theoretic Causal Inference of Lexical Flow. PhD dissertation, Eberhard-Karls-Universität Tübingen.Google Scholar
2018. Combining information-weighted sequence alignment and sound correspondence models for improved cognate detection. In Proceedings of the 27th International Conference on Computational Linguistics, 3123–3133. Shroudsburg PA: Association for Computational Linguistics. <[URL]> (permanent archive).Google Scholar
Delz, M. 2013. A Theoretical Approach to Automatic Loanword Detection. Master’s thesis, Eberhard-Karls-Universität Tübingen.Google Scholar
Dolgopolsky, A. B. 1964. Gipoteza drevnejšego rodstva jazykovych semej Severnoj Evrazii s verojatnostej točky zrenija (A probabilistic hypothesis concerning the oldest relationships among the language families of Northern Eurasia). Voprosy Jazykoznanija 2: 53–63.Google Scholar
Heeringa, W. 2004. Measuring Dialect Pronunciation Differences using Levenshtein Distance. PhD dissertation, University of Groningen.Google Scholar
IPA (International Phonetic Association). 1999. Handbook of the International Phonetic Association. Cambridge: CUP.Google Scholar
Jobling, M. A., Hurles, M. E. & Tyler-Smith, C. 2004. Human Evolutionary Genetics: Origins, Peoples and Diseases. New York NY: Garland.Google Scholar
Köllner, M. & Dellert, J. 2016. Ancestral State Reconstruction and Loanword Detection. Tübingen: Universitätsbibliothek.Google Scholar
Kondrak, G., Marcu, D. & Knight, K. 2003. Cognates can improve statistical translation models. In Proceedings of the 2003 North American Association for Computational Linguistics. Vol. 2, 46–48. Shroudsburg PA: Association for Computational Linguistics. <[URL]> (permanent archive). DOI logoGoogle Scholar
Kondrak, G. & T. Sherif. 2006. Evaluation of several phonetic similarity algorithms on the task of cognate identification. In Proceedings of the Workshop on Linguistic Distances, J. Nerbonne & E. Hinrichs (eds), 43–50. Shroudsburg PA: Association for Computational Linguistics. <[URL]> (permanent archive). DOI logoGoogle Scholar
List, J.-M. 2012. SCA: Phonetic alignment based on sound classes. In New Directions in Logic, Language and Computation [LNCS 7415], 32–51. Berlin: Springer. DOI logoGoogle Scholar
List, J.-M., Walworth, M., Greenhill, S. J., Tresoldi, T. & Forkel, R. 2018. Sequence comparison in computational historical linguistics. Journal of Language Evolution 2: 130–144. DOI logoGoogle Scholar
Manni, F. 2017. Linguistic Probes into Human History. PhD dissertation, University of Groningen.Google Scholar
Manni, F., Heeringa, W. & Nerbonne, J. 2006. To what extent are surnames words? Comparing geographic patterns of surname and dialect variation in the Netherlands. Literary and Linguistic Computing 21: 507–527. DOI logoGoogle Scholar
Mayr, E. 2002. Interview with Ernst Mayr. BioEssays 24: 960–973. DOI logoGoogle Scholar
Mennecier, P., Nerbonne, J., Heyer, E. & Manni, F. 2016. A Central Asian language survey: Collecting data, measuring relatedness and detecting loans. Language Dynamics and Change 6: 57–98. DOI logoGoogle Scholar
Mufwene, S. S. 2001. The Ecology of Language Evolution. Cambridge: CUP. DOI logoGoogle Scholar
2005. Language evolution: The population genetics way. In Gene, Sprachen, und ihre Evolution [Schriftenreihe der Universität Regensburg 29], G. Hauska (ed.), 30–52. Regensburg: Universität Regensburg.Google Scholar
2008. Language Evolution: Contact, Competition and Change. London: Bloomsbury. Google Scholar
Nerbonne, J. 2003. Linguistic variation and computation. In Proceedings of the Tenth Conference of the European Chapter of the Association for Computational Linguistics, 3–10. Shroudsburg PA: Association for Computational Linguistics. <[URL]> (permanent archive). DOI logoGoogle Scholar
2009. Data-driven dialectology. Language and Linguistics Compass 3: 175–198. DOI logoGoogle Scholar
Nerbonne, J. & Siedle, C. 2005. Dialektklassifikation auf der Grundlage aggregierter Ausspracheunterschiede. Zeitschrift für Dialektologie und Linguistik 72: 129–147.Google Scholar
Shackleton Jr., R. G. 2010. Quantitative Assessment of English-American Speech Relationships [Groningen Dissertations in Linguistics 81]. Groningen: Center for Language and Cognition Groningen.Google Scholar
Sperber, D. 1996. La Contagion des Idées. Paris: Odile Jacob.Google Scholar
Swadesh, M. 1952. Lexicostatistic dating of prehistoric ethnic contacts. Proceedings of the American Philosophical Society 96: 452–463.Google Scholar
Tukey, J. W. 1977. Exploratory Data Analysis. Reading: Addison-Wesley. Google Scholar
Wieling, M., Leinonen, T. & Nerbonne, J. 2007. Inducing sound segment differences using pair hidden Markov models. In Proceedings of 9th Meeting, Association for Computational Linguistics Special Interest Group in Computational Morphology and Phonology, 48–56. Shroudsburg PA: Association for Computational Linguistics. <[URL]> (permanent archive). DOI logoGoogle Scholar
Wieling, M., Margaretha, E. & Nerbonne, J. 2012. Inducing a measure of phonetic similarity from pronunciation variation. Journal of Phonetics 40: 307–314. DOI logoGoogle Scholar
Zhang, L. 2016. A More Sensitive Edit-Distance for Measuring Pronunciation Distances and Detecting Loanwords. Master’s thesis, University of Groningen & University of Malta.
Cited by (2)

Cited by two other publications

List, Johann-Mattis, Robert Forkel, Simon J. Greenhill, Christoph Rzymski, Johannes Englisch & Russell D. Gray
2022. Lexibank, a public repository of standardized wordlists with computed phonological and lexical features. Scientific Data 9:1 DOI logo
List, Johann-Mattis & Robert Forkel
2021. Automated identification of borrowings in multilingual wordlists. Open Research Europe 1 ► pp. 79 ff. DOI logo

This list is based on CrossRef data as of 14 november 2024. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.